Learning Transferable Features with Deep Adaptation Networks

Abstract

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers with increasing domain discrepancy. Hence, it is important to formally reduce the dataset bias and enhance the transferability in task-specific layers. In this paper, we propose a new Deep Adaptation Network (DAN) architecture, which generalizes deep convolutional neural network to the domain adaptation scenario. In DAN, hidden representations of all task-specific layers are embedded in a reproducing kernel Hilbert space where the mean embeddings of different domain distributions can be explicitly matched. The domain discrepancy is further reduced using an optimal multi-kernel selection method for mean embedding matching. DAN can learn transferable features with statistical guarantees, and can scale linearly by unbiased estimate of kernel embedding. Extensive empirical evidence shows that the proposed architecture yields state-of-the-art image classification error rates on standard domain adaptation benchmarks.

References in corpus (10)

• Improving neural networks by preventing co-adaptation of feature detectors
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• How transferable are features in deep neural networks?
• Deep Domain Confusion: Maximizing for Domain Invariance
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing
• Marginalized Denoising Autoencoders for Domain Adaptation
• Domain Adaptation: Learning Bounds and Algorithms
• Domain-Adversarial Neural Networks
• LSDA: Large Scale Detection Through Adaptation
• Domain Adaptive Neural Networks for Object Recognition

Cited by in corpus (706)

• Deep Visual Domain Adaptation: A Survey
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Deep Subdomain Adaptation Network for Image Classification
• Unsupervised Domain Adaptation with Residual Transfer Networks
• A review of domain adaptation without target labels
• Domain Separation Networks
• Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Deep Reinforcement Learning: An Overview
• Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study
• Model Adaptation: Unsupervised Domain Adaptation without Source Data
• Beyond Sharing Weights for Deep Domain Adaptation
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• A DIRT-T Approach to Unsupervised Domain Adaptation
• Kernel Mean Embedding of Distributions: A Review and Beyond
• Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks
• Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources
• Revisiting Batch Normalization For Practical Domain Adaptation
• Maximum Density Divergence for Domain Adaptation
• Cross-view Semantic Segmentation for Sensing Surroundings
• Multi-Representation Adaptation Network for Cross-domain Image Classification
• WILDS: A Benchmark of in-the-Wild Distribution Shifts
• Transfer learning for time series classification
• Wasserstein Distance based Deep Adversarial Transfer Learning for Intelligent Fault Diagnosis
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
• Bridging Theory and Algorithm for Domain Adaptation
• Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes
• A Comprehensive Survey on Transfer Learning
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• What, Where and How to Transfer in SAR Target Recognition Based on Deep CNNs
• Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation
• Deep Residual Correction Network for Partial Domain Adaptation
• Universal Domain Adaptation through Self Supervision
• Self-supervised Domain Adaptation for Computer Vision Tasks
• LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
• On Learning Invariant Representation for Domain Adaptation
• Federated Adversarial Domain Adaptation
• Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild
• Cross-Subject Transfer Learning in Human Activity Recognition Systems using Generative Adversarial Networks
• Third-Person Imitation Learning
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• A Deeper Look at Facial Expression Dataset Bias
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
• One Million Scenes for Autonomous Driving: ONCE Dataset
• Learning Disentangled Semantic Representation for Domain Adaptation
• Learning to cluster in order to transfer across domains and tasks
• Universal representations:The missing link between faces, text, planktons, and cat breeds
• Deep Transfer Learning with Joint Adaptation Networks
• CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
• Memory-aware curriculum federated learning for breast cancer classification
• Unsupervised Domain Adaptation with Adversarial Residual Transform Networks
• Return of Frustratingly Easy Domain Adaptation
• Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
• Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice
• Integrating Expert Knowledge with Domain Adaptation for Unsupervised Fault Diagnosis
• Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
• Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
• Causally Regularized Learning with Agnostic Data Selection Bias
• Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift
• Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network
• Multi-Adversarial Domain Adaptation
• Demystifying Neural Style Transfer
• Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification
• Generalizing to unseen domains via distribution matching
• Optimal Bayesian Transfer Learning
• Self-supervised Autoregressive Domain Adaptation for Time Series Data
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
• Multi-label Learning Based Deep Transfer Neural Network for Facial Attribute Classification
• Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation
• TDACNN: Target-domain-free Domain Adaptation Convolutional Neural Network for Drift Compensation in Gas Sensors
• DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
• Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation
• Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
• Semi-supervised Domain Adaptation via Minimax Entropy
• Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
• Modeling Users' Behavior Sequences with Hierarchical Explainable Network for Cross-domain Fraud Detection
• Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
• Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
• Missing-Class-Robust Domain Adaptation by Unilateral Alignment for Fault Diagnosis
• Generalized Domain Conditioned Adaptation Network
• Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
• Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
• Sample-to-Sample Correspondence for Unsupervised Domain Adaptation
• Fully Convolutional Adaptation Networks for Semantic Segmentation
• Synthesizing Training Images for Boosting Human 3D Pose Estimation
• Cycle Self-Training for Domain Adaptation
• Large sample analysis of the median heuristic
• Learning Transferable Parameters for Unsupervised Domain Adaptation
• Unsupervised Person Re-identification by Soft Multilabel Learning
• FDA: Fourier Domain Adaptation for Semantic Segmentation
• Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities
• Self-ensembling for visual domain adaptation
• Damage detection using in-domain and cross-domain transfer learning
• Multi-modal Deep Analysis for Multimedia
• Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospective
• Small Sample Learning in Big Data Era
• Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
• On Leveraging Pretrained GANs for Generation with Limited Data
• Dynamic Instance Domain Adaptation
• Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift
• Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
• Transferrable Prototypical Networks for Unsupervised Domain Adaptation
• Adversarial Dropout Regularization
• FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
• Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
• Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
• Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment
• Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies
• Virtual Mixup Training for Unsupervised Domain Adaptation
• Learning Causal Semantic Representation for Out-of-Distribution Prediction
• Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation
• Adversarial Domain Adaptation with Prototype-Based Normalized Output Conditioner
• Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation
• PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network with a Benchmark at Cross-modality Cardiac Segmentation
• Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection
• Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentation
• KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
• SpotTune: Transfer Learning through Adaptive Fine-tuning
• Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
• Triplet Similarity Embedding for Face Verification
• Learning Target Domain Specific Classifier for Partial Domain Adaptation
• Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation
• Deep Transparent Prediction through Latent Representation Analysis
• LogME: Practical Assessment of Pre-trained Models for Transfer Learning
• Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach
• Domain Adaptation for Semantic Segmentation with Maximum Squares Loss
• Domain-Symmetric Networks for Adversarial Domain Adaptation
• Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets
• Domain Adaptive Person Re-Identification via Coupling Optimization
• Unsupervised Domain Adaptation of Black-Box Source Models
• A Survey on Deep Transfer Learning
• GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation
• Robust Domain Misinformation Detection via Multi-modal Feature Alignment
• Inferring Latent Domains for Unsupervised Deep Domain Adaptation
• Rethinking Distributional Matching Based Domain Adaptation
• SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
• Learning to Transfer Examples for Partial Domain Adaptation
• Learning to Adapt Invariance in Memory for Person Re-identification
• Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
• Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation
• Learning Weighted Representations for Generalization Across Designs
• PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation
• Confidence Regularized Self-Training
• A Survey on Deep Learning of Small Sample in Biomedical Image Analysis
• AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification
• Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
• Racial Faces in-the-Wild: Reducing Racial Bias by Information Maximization Adaptation Network
• Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects
• Adversarial-Prediction Guided Multi-task Adaptation for Semantic Segmentation of Electron Microscopy Images
• Domain Adaptive Attention Learning for Unsupervised Person Re-Identification
• Transfer Learning with Dynamic Adversarial Adaptation Network
• Federated Learning with Additional Mechanisms on Clients to Reduce Communication Costs
• Smartphone Sensor-based Human Activity Recognition Robust to Different Sampling Rates
• Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner
• Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes
• Exploring Object Relation in Mean Teacher for Cross-Domain Detection
• Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation
• Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection
• Constrained domain adaptation for Image segmentation
• Semi-Supervised QA with Generative Domain-Adaptive Nets
• Source Free Domain Adaptation with Image Translation
• An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training
• Transfer Learning for Speech and Language Processing
• 3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings
• Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay
• Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics
• Exploring Categorical Regularization for Domain Adaptive Object Detection
• Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification
• Multiple Source Domain Adaptation with Adversarial Training of Neural Networks
• Transfer Learning with Label Noise
• Decoupled Adaptation for Cross-Domain Object Detection
• Partial Adversarial Domain Adaptation
• Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition
• Transfer of Machine Learning Fairness across Domains
• Episodic Training for Domain Generalization
• Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation
• Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results
• Domain Adaptation as a Problem of Inference on Graphical Models
• Domain Aggregation Networks for Multi-Source Domain Adaptation
• SPIGAN: Privileged Adversarial Learning from Simulation
• Domain-Specific Batch Normalization for Unsupervised Domain Adaptation
• Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains
• Minimum Class Confusion for Versatile Domain Adaptation
• Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations
• Learning to Generate Novel Domains for Domain Generalization
• Privacy Sensitive Speech Analysis Using Federated Learning to Assess Depression
• Robust Local Preserving and Global Aligning Network for Adversarial Domain Adaptation
• Multimodal Across Domains Gaze Target Detection
• Domain Adaptation without Source Data
• Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
• A Prototype-Oriented Framework for Unsupervised Domain Adaptation
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
• TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation
• Cross Modal Distillation for Supervision Transfer
• No More Discrimination: Cross City Adaptation of Road Scene Segmenters
• Harmonizing Transferability and Discriminability for Adapting Object Detectors
• Progressive Feature Alignment for Unsupervised Domain Adaptation
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Test-time Batch Statistics Calibration for Covariate Shift
• Self-Supervised Training Enhances Online Continual Learning
• Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
• Similarity-preserving Image-image Domain Adaptation for Person Re-identification
• RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
• Multi-step Online Unsupervised Domain Adaptation
• Deep Learning for Scene Classification: A Survey
• Learning Kernel for Conditional Moment-Matching Discrepancy-based Image Classification
• Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data
• Joint Contrastive Learning for Unsupervised Domain Adaptation
• SALIENCE: An Unsupervised User Adaptation Model for Multiple Wearable Sensors Based Human Activity Recognition
• Open Set Domain Adaptation by Backpropagation
• DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
• SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
• Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization
• Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation
• Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation
• Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds
• Cluster Alignment with a Teacher for Unsupervised Domain Adaptation
• Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation
• Towards Non-I.I.D. Image Classification: A Dataset and Baselines
• Transformer-Based Source-Free Domain Adaptation
• Importance Weighted Adversarial Nets for Partial Domain Adaptation
• Causal Generative Domain Adaptation Networks
• See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation
• DiDA: Disentangled Synthesis for Domain Adaptation
• Coupling Adversarial Learning with Selective Voting Strategy for Distribution Alignment in Partial Domain Adaptation
• Rethink Maximum Mean Discrepancy for Domain Adaptation
• Close Yet Distinctive Domain Adaptation
• Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification
• Transferable Calibration with Lower Bias and Variance in Domain Adaptation
• Transfer Metric Learning: Algorithms, Applications and Outlooks
• DSDANet: Deep Siamese Domain Adaptation Convolutional Neural Network for Cross-domain Change Detection
• Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation
• Towards Shape Biased Unsupervised Representation Learning for Domain Generalization
• Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation
• Unbiased Mean Teacher for Cross-domain Object Detection
• Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation
• Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond
• Cross-domain Detection via Graph-induced Prototype Alignment
• Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning
• Domain Adaptation for Time Series Forecasting via Attention Sharing
• Regularizing Proxies with Multi-Adversarial Training for Unsupervised Domain-Adaptive Semantic Segmentation
• BreakingNews: Article Annotation by Image and Text Processing
• A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification
• Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
• Knowledge Projection for Deep Neural Networks
• Prototypical Partial Optimal Transport for Universal Domain Adaptation
• Characterizing and Avoiding Negative Transfer
• Out-of-distribution Prediction with Invariant Risk Minimization: The Limitation and An Effective Fix
• BCGGAN: Ballistocardiogram artifact removal in simultaneous EEG-fMRI using generative adversarial network
• Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition
• Transferability of Natural Language Inference to Biomedical Question Answering
• Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
• Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
• Image Generation From Small Datasets via Batch Statistics Adaptation
• MixStyle Neural Networks for Domain Generalization and Adaptation
• Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
• Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners
• Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels
• Dual Mixup Regularized Learning for Adversarial Domain Adaptation
• Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector
• Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learning
• Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization
• Cross-domain Contrastive Learning for Unsupervised Domain Adaptation
• OVANet: One-vs-All Network for Universal Domain Adaptation
• AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
• Gradually Vanishing Bridge for Adversarial Domain Adaptation
• Wasserstein Distance Based Domain Adaptation for Object Detection
• Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption
• Constructing Deep Neural Networks by Bayesian Network Structure Learning
• Improving Domain Adaptation Through Class Aware Frequency Transformation
• Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark
• Open-Set Hypothesis Transfer with Semantic Consistency
• Progressive Domain Expansion Network for Single Domain Generalization
• Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer
• LiDARNet: A Boundary-Aware Domain Adaptation Model for Point Cloud Semantic Segmentation
• SPLAT: Semantic Pixel-Level Adaptation Transforms for Detection
• Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning
• Mutual Learning Network for Multi-Source Domain Adaptation
• Entropy Minimization vs. Diversity Maximization for Domain Adaptation
• Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation
• Unifying Unsupervised Domain Adaptation and Zero-Shot Visual Recognition
• Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
• Scalable Greedy Algorithms for Transfer Learning
• Learning Factorized Representations for Open-set Domain Adaptation
• ConDA: Continual Unsupervised Domain Adaptation
• A Comprehensive Analysis of Information Leakage in Deep Transfer Learning
• Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification
• CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation
• Attention Regularized Laplace Graph for Domain Adaptation
• SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation
• Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation
• Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation
• Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance
• Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs
• Dynamic Weighted Learning for Unsupervised Domain Adaptation
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
• Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation
• Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
• Network Architecture Search for Domain Adaptation
• Multi-Task Domain Adaptation for Deep Learning of Instance Grasping from Simulation
• OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation
• Improving Compound Activity Classification via Deep Transfer and Representation Learning
• Cross-Domain Visual Recognition via Domain Adaptive Dictionary Learning
• Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
• Exploiting Domain Transferability for Collaborative Inter-level Domain Adaptive Object Detection
• Angular Visual Hardness
• Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning
• Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings
• Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation
• Efficient Deep Neural Networks
• Unsupervised Domain Adaptation with Random Walks on Target Labelings
• Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis
• Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling
• Discriminative Label Consistent Domain Adaptation
• Few-Shot Learning as Domain Adaptation: Algorithm and Analysis
• Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training
• ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
• Multi-Modal Detection of Alzheimer's Disease from Speech and Text
• Associative Partial Domain Adaptation
• VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation
• Transfering Low-Frequency Features for Domain Adaptation
• Domain Adaptation from Synthesis to Reality in Single-model Detector for Video Smoke Detection
• MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation
• Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
• Open Set Domain Adaptation: Theoretical Bound and Algorithm
• DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification
• Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation
• Delving Deep into the Generalization of Vision Transformers under Distribution Shifts
• Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning
• Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding
• Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation
• Learning from a Complementary-label Source Domain: Theory and Algorithms
• Dual Adversarial Domain Adaptation
• Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation
• A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes
• Learning Cross-domain Generalizable Features by Representation Disentanglement
• Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation
• Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation
• Domain Adaptation with Auxiliary Target Domain-Oriented Classifier
• Domain Attention Consistency for Multi-Source Domain Adaptation
• Semantics-Aware Image to Image Translation and Domain Transfer
• Adaptive Consistency Regularization for Semi-Supervised Transfer Learning
• Adversarial Cross-Domain Action Recognition with Co-Attention
• Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation
• Adversarial Domain Adaptation with Domain Mixup
• Benchmarking the Robustness of Instance Segmentation Models
• Domain Adaptive Medical Image Segmentation via Adversarial Learning of Disease-Specific Spatial Patterns
• AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
• Aggregate or Not? Exploring Where to Privatize in DNN Based Federated Learning Under Different Non-IID Scenes
• ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation
• Style Normalization and Restitution for Domain Generalization and Adaptation
• Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation
• Attending to Discriminative Certainty for Domain Adaptation
• Unsupervised Multi-Source Domain Adaptation for Person Re-Identification
• Known-class Aware Self-ensemble for Open Set Domain Adaptation
• Open Domain Generalization with Domain-Augmented Meta-Learning
• FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
• A Theory of Label Propagation for Subpopulation Shift
• Causally motivated Shortcut Removal Using Auxiliary Labels
• Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer
• Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification
• A Unified Joint Maximum Mean Discrepancy for Domain Adaptation
• Data Augmentation with norm-VAE for Unsupervised Domain Adaptation
• Domain Adaptation Gaze Estimation by Embedding with Prediction Consistency
• Deep Domain-Adversarial Image Generation for Domain Generalisation
• An Adversarial Domain Separation Framework for Septic Shock Early Prediction Across EHR Systems
• Adversarial Bi-Regressor Network for Domain Adaptive Regression
• Adversarial-Learned Loss for Domain Adaptation
• Maximum Mean Discrepancy for Generalization in the Presence of Distribution and Missingness Shift
• HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation
• RSA: Randomized Simulation as Augmentation for Robust Human Action Recognition
• Domain Adaptation Using Adversarial Learning for Autonomous Navigation
• Multi-source Distilling Domain Adaptation
• Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation
• PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities
• SOSELETO: A Unified Approach to Transfer Learning and Training with Noisy Labels
• IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
• DINE: Domain Adaptation from Single and Multiple Black-box Predictors
• When Invariant Representation Learning Meets Label Shift: Insufficiency and Theoretical Insights
• RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer
• Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation
• Deep Adversarial Transition Learning using Cross-Grafted Generative Stacks
• Curriculum based Dropout Discriminator for Domain Adaptation
• Class-imbalanced Domain Adaptation: An Empirical Odyssey
• Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction
• Unsupervised Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation via Semi-supervised Learning and Label Fusion
• When Naïve Bayes Nearest Neighbours Meet Convolutional Neural Networks
• Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
• Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
• Adversarial Domain Adaptation for Machine Reading Comprehension
• Learning Sampling Policies for Domain Adaptation
• Learning Smooth Representation for Unsupervised Domain Adaptation
• Camera Adaptation for Fundus-Image-Based CVD Risk Estimation
• Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment
• Critical Assessment of Transfer Learning for Medical Image Segmentation with Fully Convolutional Neural Networks
• Towards Domain Invariant Single Image Dehazing
• The Battleship Approach to the Low Resource Entity Matching Problem
• MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
• Attention-Privileged Reinforcement Learning
• Adversarial Attribute-Image Person Re-identification
• Domain-Adaptive Few-Shot Learning
• Learning From Less Data: Diversified Subset Selection and Active Learning in Image Classification Tasks
• Learning to Match Distributions for Domain Adaptation
• Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation
• Transfer Learning with Bellwethers to find Good Configurations
• DAN: Dual-View Representation Learning for Adapting Stance Classifiers to New Domains
• Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Recognition
• Domain Adaptation for Image Dehazing
• Toward a better trade-off between performance and fairness with kernel-based distribution matching
• Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensors
• Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation
• Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation
• Discriminative Joint Probability Maximum Mean Discrepancy (DJP-MMD) for Domain Adaptation
• A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
• Exploiting Local Feature Patterns for Unsupervised Domain Adaptation
• One-Shot Unsupervised Cross-Domain Detection
• On Deep Domain Adaptation: Some Theoretical Understandings
• Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving
• Cross-Entropy Adversarial View Adaptation for Person Re-identification
• Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation
• CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
• I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
• Learning Transferable UAV for Forest Visual Perception
• A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
• Factorized Adversarial Networks for Unsupervised Domain Adaptation
• A Cross-Level Information Transmission Network for Predicting Phenotype from New Genotype: Application to Cancer Precision Medicine
• Selective Transfer with Reinforced Transfer Network for Partial Domain Adaptation
• Domain-Specific Suppression for Adaptive Object Detection
• Secure Domain Adaptation with Multiple Sources
• Privacy-preserving Transfer Learning via Secure Maximum Mean Discrepancy
• Stretching Domain Adaptation: How far is too far?
• Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training
• BiPC: Bidirectional Probability Calibration for Unsupervised Domain Adaption
• Learning Depth from Monocular Videos Using Synthetic Data: A Temporally-Consistent Domain Adaptation Approach
• Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
• AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning
• Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning
• Unsupervised Deep Feature Transfer for Low Resolution Image Classification
• Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
• Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
• Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment
• Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration
• Towards Backward-Compatible Representation Learning
• Multi-Source Video Domain Adaptation with Temporal Attentive Moment Alignment
• Intelligent Icing Detection Model of Wind Turbine Blades Based on SCADA data
• Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection
• CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion
• A Fine-Grained Analysis on Distribution Shift
• Towards Principled Disentanglement for Domain Generalization
• Cross-Region Domain Adaptation for Class-level Alignment
• Learning to Diversify for Single Domain Generalization
• Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments
• ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation
• Joint Semantic Domain Alignment and Target Classifier Learning for Unsupervised Domain Adaptation
• Towards Discriminative Representation Learning for Unsupervised Person Re-identification
• Unsupervised Domain Adaptation for Spatio-Temporal Action Localization
• Emotion controllable speech synthesis using emotion-unlabeled dataset with the assistance of cross-domain speech emotion recognition
• Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
• Are We Hungry for 3D LiDAR Data for Semantic Segmentation? A Survey and Experimental Study
• Context-Aware Domain Adaptation in Semantic Segmentation
• Cycle-consistent Conditional Adversarial Transfer Networks
• Structure-Attentioned Memory Network for Monocular Depth Estimation
• Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation
• DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation
• Towards Corruption-Agnostic Robust Domain Adaptation
• Moment-Based Domain Adaptation: Learning Bounds and Algorithms
• Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting
• Identity Preserving Generative Adversarial Network for Cross-Domain Person Re-identification
• Part-level Car Parsing and Reconstruction from Single Street View
• On Localized Discrepancy for Domain Adaptation
• Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment
• Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld
• Domain Adaptation with Randomized Expectation Maximization
• MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
• Union-set Multi-source Model Adaptation for Semantic Segmentation
• Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss
• Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separation
• Featurized Density Ratio Estimation
• ADMP: An Adversarial Double Masks Based Pruning Framework For Unsupervised Cross-Domain Compression
• Learning Domain Adaptive Features with Unlabeled Domain Bridges
• Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis Transfer
• CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
• Revisiting Mid-Level Patterns for Cross-Domain Few-Shot Recognition
• Domain Adaptation Meets Disentangled Representation Learning and Style Transfer
• Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction
• SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
• Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Gradual Domain Adaptation via Self-Training of Auxiliary Models
• Transfer Learning Toolkit: Primers and Benchmarks
• Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification
• Cost-Effective Training of Deep CNNs with Active Model Adaptation
• Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
• Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation
• Deep Cross-media Knowledge Transfer
• Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
• GAN Memory with No Forgetting
• Energy-constrained Self-training for Unsupervised Domain Adaptation
• Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection
• Neural Task Representations as Weak Supervision for Model Agnostic Cross-Lingual Transfer
• Robustified Domain Adaptation
• A General Upper Bound for Unsupervised Domain Adaptation
• Semi-supervised Collaborative Filtering by Text-enhanced Domain Adaptation
• Learning Cross-modal Contrastive Features for Video Domain Adaptation
• Teacher Model Fingerprinting Attacks Against Transfer Learning
• Transferable Time-Series Forecasting under Causal Conditional Shift
• Analog-to-digital conversion revolutionized by deep learning
• Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation
• Weakly-supervised Domain Adaption for Aspect Extraction via Multi-level Interaction Transfer
• Cross-Domain Adversarial Auto-Encoder
• Learning to Align Multi-Camera Domains using Part-Aware Clustering for Unsupervised Video Person Re-Identification
• Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation
• Unsupervised Domain Adaptation using Generative Models and Self-ensembling
• Heterogeneous Domain Adaptation via Soft Transfer Network
• Universal Domain Adaptation in Ordinal Regression
• Multi-Anchor Active Domain Adaptation for Semantic Segmentation
• On the Behavior of Convolutional Nets for Feature Extraction
• A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation
• GradMix: Multi-source Transfer across Domains and Tasks
• Preserving Semantic Consistency in Unsupervised Domain Adaptation Using Generative Adversarial Networks
• Representation Transfer by Optimal Transport
• Target Aware Network Adaptation for Efficient Representation Learning
• Unsupervised Transductive Domain Adaptation
• Self-adaptive Re-weighted Adversarial Domain Adaptation
• Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits
• AutoAdapt: Automated Segmentation Network Search for Unsupervised Domain Adaptation
• Visualizing Adapted Knowledge in Domain Transfer
• Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation
• Unsupervised domain adaptation via double classifiers based on high confidence pseudo label
• The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation
• Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
• Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection
• Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification
• Disentanglement Then Reconstruction: Learning Compact Features for Unsupervised Domain Adaptation
• Structured Discriminative Tensor Dictionary Learning for Unsupervised Domain Adaptation
• Attention-Aware Age-Agnostic Visual Place Recognition
• Multimodal Deep Domain Adaptation
• Domain Contrast for Domain Adaptive Object Detection
• Packaging and Sharing Machine Learning Models via the Acumos AI Open Platform
• Unsupervised Domain Attention Adaptation Network for Caricature Attribute Recognition
• Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
• Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
• Target Consistency for Domain Adaptation: when Robustness meets Transferability
• Stochastic Adversarial Gradient Embedding for Active Domain Adaptation
• Adversarial Deep Network Embedding for Cross-network Node Classification
• Mining Label Distribution Drift in Unsupervised Domain Adaptation
• A Bayesian Approach to (Online) Transfer Learning: Theory and Algorithms
• Subjective Question Answering: Deciphering the inner workings of Transformers in the realm of subjectivity
• Learning from Synthetic Animals
• Adversarial Robustness for Unsupervised Domain Adaptation
• Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm
• Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
• Learning Invariant Representations across Domains and Tasks
• A Fully Convolutional Tri-branch Network (FCTN) for Domain Adaptation
• Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks
• AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
• Transporting Causal Mechanisms for Unsupervised Domain Adaptation
• Spatial-Aware GAN for Unsupervised Person Re-identification
• Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources
• Self-Supervised Domain Adaptation with Consistency Training
• Multi-source Few-shot Domain Adaptation
• Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation
• Sequential Learning for Domain Generalization
• Spectral Unsupervised Domain Adaptation for Visual Recognition
• Representation Bayesian Risk Decompositions and Multi-Source Domain Adaptation
• Parameter Transfer Unit for Deep Neural Networks
• OmniPrint: A Configurable Printed Character Synthesizer
• Subdomain Adaptation with Manifolds Discrepancy Alignment
• Adaptive Deep Learning for Entity Resolution by Risk Analysis
• Tackling Imbalanced Data in Cybersecurity with Transfer Learning: A Case with ROP Payload Detection
• Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain Adaptation
• Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
• Domain Adaptation on Semantic Segmentation with Separate Affine Transformation in Batch Normalization
• Domain Adaptation on Semantic Segmentation for Aerial Images
• Metric-Learning-Assisted Domain Adaptation
• Augmenting Transfer Learning with Semantic Reasoning
• Towards Recognizing New Semantic Concepts in New Visual Domains
• Efficient Multi-Domain Network Learning by Covariance Normalization
• Adversarial Feature Training for Generalizable Robotic Visuomotor Control
• Matching Embeddings for Domain Adaptation
• Discriminative Noise Robust Sparse Orthogonal Label Regression-based Domain Adaptation
• Traffic Flow Estimation using LTE Radio Frequency Counters and Machine Learning
• A General Data Renewal Model for Prediction Algorithms in Industrial Data Analytics
• Attract or Distract: Exploit the Margin of Open Set
• Detecting Bias in Transfer Learning Approaches for Text Classification
• Unsupervised Domain Adaptation Network with Category-Centric Prototype Aligner for Biomedical Image Segmentation
• Learning Interpretable Microscopic Features of Tumor by Multi-task Adversarial CNNs To Improve Generalization
• Domain Adaptation without Model Transferring
• Unveiling Class-Labeling Structure for Universal Domain Adaptation
• On Direct Distribution Matching for Adapting Segmentation Networks
• Teacher-Student Consistency For Multi-Source Domain Adaptation
• Post-Hoc Domain Adaptation via Guided Data Homogenization
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection
• Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases
• A Joint Pixel and Feature Alignment Framework for Cross-dataset Palmprint Recognition
• Unsupervised Domain Expansion from Multiple Sources
• Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation
• Learning the Compositional Spaces for Generalized Zero-shot Learning
• Regressive Domain Adaptation for Unsupervised Keypoint Detection
• Unsupervised Object Matching for Relational Data
• Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery
• Look, Cast and Mold: Learning 3D Shape Manifold from Single-view Synthetic Data
• Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptation
• ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale
• More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation
• Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks
• Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation
• Online Continual Adaptation with Active Self-Training
• Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation
• 2021 BEETL Competition: Advancing Transfer Learning for Subject Independence & Heterogenous EEG Data Sets
• On the Robustness of Domain Adaption to Adversarial Attacks
• Conditional Bures Metric for Domain Adaptation
• Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection
• Semi-Supervised Adversarial Discriminative Domain Adaptation
• On Label Shift in Domain Adaptation via Wasserstein Distance
• Collaborative Semantic Aggregation and Calibration for Federated Domain Generalization
• Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift
• One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
• Adv-4-Adv: Thwarting Changing Adversarial Perturbations via Adversarial Domain Adaptation
• Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation
• Meta-learning Transferable Representations with a Single Target Domain
• Defocus Blur Detection via Salient Region Detection Prior
• Open Set Domain Recognition via Attention-Based GCN and Semantic Matching Optimization
• Adversarial Domain Randomization
• Exploring Data Aggregation and Transformations to Generalize across Visual Domains
• Generalized Domain Adaptation
• PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python
• Robust Ensembling Network for Unsupervised Domain Adaptation
• Mutual Information-based Disentangled Neural Networks for Classifying Unseen Categories in Different Domains: Application to Fetal Ultrasound Imaging
• Zero-Shot Recognition via Optimal Transport
• Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark
• Shared Predictive Cross-Modal Deep Quantization
• Action Segmentation with Mixed Temporal Domain Adaptation
• Ensemble Multi-Source Domain Adaptation with Pseudolabels
• Active Learning for Deep Neural Networks on Edge Devices
• Teacher-Student Competition for Unsupervised Domain Adaptation
• Frustratingly Easy Uncertainty Estimation for Distribution Shift
• Learning Synthetic to Real Transfer for Localization and Navigational Tasks
• Learning to Generalize One Sample at a Time with Self-Supervision
• Cross-Domain Latent Modulation for Variational Transfer Learning
• Deep Adversarial Domain Adaptation Based on Multi-layer Joint Kernelized Distance
• Wasserstein Distance Guided Cross-Domain Learning
• Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement
• Towards Fair Cross-Domain Adaptation via Generative Learning
• ADeLA: Automatic Dense Labeling with Attention for Viewpoint Adaptation in Semantic Segmentation
• Densely Semantic Enhancement for Domain Adaptive Region-free Detectors
• Dynamic Domain Adaptation for Efficient Inference
• Geometry-Aware Unsupervised Domain Adaptation for Stereo Matching
• Contrastive Domain Adaptation for Question Answering using Limited Text Corpora
• Transferable Semantic Augmentation for Domain Adaptation
• Cross-Modality Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation
• Dynamic Transfer for Multi-Source Domain Adaptation
• Deep Least Squares Alignment for Unsupervised Domain Adaptation
• Adversarial Transfer Learning for Cross-domain Visual Recognition
• Importance Filtered Cross-Domain Adaptation
• When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
• Exploring Dropout Discriminator for Domain Adaptation
• Hard Class Rectification for Domain Adaptation
• Dataset Bias in Few-shot Image Recognition
• Relation-aware Meta-learning for Market Segment Demand Prediction with Limited Records
• Open Set Domain Adaptation for Image and Action Recognition
• SARS-CoV-2 virus RNA sequence classification and geographical analysis with convolutional neural networks approach
• Domain-Specific Bias Filtering for Single Labeled Domain Generalization
• Mixed Set Domain Adaptation
• Cross-domain error minimization for unsupervised domain adaptation
• Forecasting Daily COVID-19 Related Calls in VA Health Care System: Predictive Model Development
• CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency
• Knothe-Rosenblatt transport for Unsupervised Domain Adaptation
• Modality Compensation Network: Cross-Modal Adaptation for Action Recognition
• Deep Domain Adaptation for Pavement Crack Detection
• On-target Adaptation
• Domain Adaptation by Maximizing Population Correlation with Neural Architecture Search
• Synthetic-to-Real Domain Adaptation for Lane Detection
• Semi-Supervised Domain Generalization with Evolving Intermediate Domain
• Self-Calibrating Indoor Localization with Crowdsourcing Fingerprints and Transfer Learning
• Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation
• LRS-DAG: Low Resource Supervised Domain Adaptation with Generalization Across Domains
• Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment
• Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation
• Cross Domain Image Matching in Presence of Outliers
• Dirty Pixels: Towards End-to-End Image Processing and Perception
• Subject Enveloped Deep Sample Fuzzy Ensemble Learning Algorithm of Parkinson's Speech Data
• Universal Multi-Source Domain Adaptation
• Deep Domain Adaptation under Deep Label Scarcity
• Zero-Round Active Learning
• Deep Doubly Supervised Transfer Network for Diagnosis of Breast Cancer with Imbalanced Ultrasound Imaging Modalities
• Learning color space adaptation from synthetic to real images of cirrus clouds
• Learning to see across Domains and Modalities
• Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
• Deep Transfer Learning for EEG-based Brain Computer Interface
• Dynamic Adaptation on Non-Stationary Visual Domains
• Unsupervised Domain Adaptation: A Reality Check
• Domain Adaptation with Morphologic Segmentation
• Leveraging Motion Priors in Videos for Improving Human Segmentation
• Domain Adaptation with Incomplete Target Domains
• CHEER: Rich Model Helps Poor Model via Knowledge Infusion
• Efficient Video Understanding via Layered Multi Frame-Rate Analysis
• Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection
• Image-to-Image Translation of Synthetic Samples for Rare Classes
• Deep Spherical Manifold Gaussian Kernel for Unsupervised Domain Adaptation
• 3D Scene Parsing via Class-Wise Adaptation
• Online Domain Adaptation for Continuous Cross-Subject Liver Viability Evaluation Based on Irregular Thermal Data
• Towards Visual Feature Translation
• Unsupervised Domain Adaptation in the Wild: Dealing with Asymmetric Label Sets
• Domain Adaptation for Facial Expression Classifier via Domain Discrimination and Gradient Reversal