Deep Domain Confusion: Maximizing for Domain Invariance

Abstract

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning deep models in a new domain can require a significant amount of data, which for many applications is simply not available. We propose a new CNN architecture which introduces an adaptation layer and an additional domain confusion loss, to learn a representation that is both semantically meaningful and domain invariant. We additionally show that a domain confusion metric can be used for model selection to determine the dimension of an adaptation layer and the best position for the layer in the CNN architecture. Our proposed adaptation method offers empirical performance which exceeds previously published results on a standard benchmark visual domain adaptation task.

References in corpus (5)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Frustratingly Easy Domain Adaptation
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• Domain Adaptation: Learning Bounds and Algorithms
• Domain Adaptive Neural Networks for Object Recognition

Cited by in corpus (465)

• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Deep Visual Domain Adaptation: A Survey
• Deep Subdomain Adaptation Network for Image Classification
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics -- A Comprehensive Review
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Domain Separation Networks
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• 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
• Adversarial Discriminative Domain Adaptation
• Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources
• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
• Revisiting Batch Normalization For Practical Domain Adaptation
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Maximum Density Divergence for Domain Adaptation
• Like What You Like: Knowledge Distill via Neuron Selectivity Transfer
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Multi-Representation Adaptation Network for Cross-domain Image Classification
• WILDS: A Benchmark of in-the-Wild Distribution Shifts
• Wasserstein Distance based Deep Adversarial Transfer Learning for Intelligent Fault Diagnosis
• Towards Out-Of-Distribution Generalization: A Survey
• Bridging Theory and Algorithm for Domain Adaptation
• Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes
• A Comprehensive Survey on Transfer Learning
• One-Shot Imitation Learning
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• What, Where and How to Transfer in SAR Target Recognition Based on Deep CNNs
• A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions
• Few-Shot Adversarial Domain Adaptation
• Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
• Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
• A Berkeley View of Systems Challenges for AI
• Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation
• Deep Residual Correction Network for Partial Domain Adaptation
• LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
• Universal Domain Adaptation through Self Supervision
• A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
• Federated Adversarial Domain Adaptation
• Third-Person Imitation Learning
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Learning Disentangled Semantic Representation for Domain Adaptation
• Learning to cluster in order to transfer across domains and tasks
• Deep Transfer Learning with Joint Adaptation Networks
• CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
• One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
• Return of Frustratingly Easy Domain Adaptation
• Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
• Deep Domain Adaptation Based Video Smoke Detection using Synthetic Smoke Images
• Coupled Generative Adversarial Networks
• Contrastive Adaptation Network for Unsupervised Domain Adaptation
• Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine
• Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
• Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network
• Multi-Adversarial Domain Adaptation
• Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification
• Demystifying Neural Style Transfer
• Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
• Self-supervised Autoregressive Domain Adaptation for Time Series Data
• TDACNN: Target-domain-free Domain Adaptation Convolutional Neural Network for Drift Compensation in Gas Sensors
• Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
• Semi-supervised Domain Adaptation via Minimax Entropy
• Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
• On The Effects Of Data Normalisation For Domain Adaptation On EEG Data
• Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation
• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
• Generalized Domain Conditioned Adaptation Network
• Sample-to-Sample Correspondence for Unsupervised Domain Adaptation
• Synthesizing Training Images for Boosting Human 3D Pose Estimation
• Fully Convolutional Adaptation Networks for Semantic Segmentation
• Partial Transfer Learning with Selective Adversarial Networks
• TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimation
• Self-ensembling for visual domain adaptation
• Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning
• Multi-modal Deep Analysis for Multimedia
• Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
• Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment
• COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19
• Toward cross-subject and cross-session generalization in EEG-based emotion recognition: Systematic review, taxonomy, and methods
• A Survey on Transfer Learning in Natural Language Processing
• Label Efficient Learning of Transferable Representations across Domains and Tasks
• Contrastive Domain Adaptation for Time-Series via Temporal Mixup
• Dynamic Instance Domain Adaptation
• Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
• Adversarial Dropout Regularization
• Transferrable Prototypical Networks for Unsupervised Domain Adaptation
• Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matching
• Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment
• Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
• Moment Matching for Multi-Source Domain Adaptation
• Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies
• FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare
• Adversarial Domain Adaptation with Prototype-Based Normalized Output Conditioner
• PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network with a Benchmark at Cross-modality Cardiac Segmentation
• Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation
• 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
• Object Detection Using Deep CNNs Trained on Synthetic Images
• KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
• Learning Target Domain Specific Classifier for Partial Domain Adaptation
• Knowledge Adaptation: Teaching to Adapt
• Domain-Symmetric Networks for Adversarial Domain Adaptation
• Domain Adaptation for Semantic Segmentation with Maximum Squares Loss
• A Survey on Deep Transfer Learning
• Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning
• Learning to Transfer Examples for Partial Domain Adaptation
• Feature Alignment and Restoration for Domain Generalization and Adaptation
• PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation
• Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss
• Confidence Regularized Self-Training
• Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels
• AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification
• Racial Faces in-the-Wild: Reducing Racial Bias by Information Maximization Adaptation Network
• Self-Supervised Learning for Domain Adaptation on Point-Clouds
• Adversarial-Prediction Guided Multi-task Adaptation for Semantic Segmentation of Electron Microscopy Images
• Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
• Federated Learning with Additional Mechanisms on Clients to Reduce Communication Costs
• Transfer Learning with Dynamic Adversarial Adaptation Network
• Domain Adaptive Attention Learning for Unsupervised Person Re-Identification
• Smartphone Sensor-based Human Activity Recognition Robust to Different Sampling Rates
• PPFS: Predictive Permutation Feature Selection
• An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training
• Constrained domain adaptation for Image segmentation
• Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition
• Decoupled Adaptation for Cross-Domain Object Detection
• Partial Adversarial Domain Adaptation
• Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation
• Episodic Training for Domain Generalization
• Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results
• Scalable Transfer Learning with Expert Models
• Discriminative Radial Domain Adaptation
• SPIGAN: Privileged Adversarial Learning from Simulation
• Minimum Class Confusion for Versatile Domain Adaptation
• Image to Image Translation for Domain Adaptation
• Robust Local Preserving and Global Aligning Network for Adversarial Domain Adaptation
• Domain-Specific Batch Normalization for Unsupervised Domain Adaptation
• TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation
• Domain Adaptation without Source Data
• A Prototype-Oriented Framework for Unsupervised Domain Adaptation
• Cross Modal Distillation for Supervision Transfer
• Harmonizing Transferability and Discriminability for Adapting Object Detectors
• DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations
• Progressive Feature Alignment for Unsupervised Domain Adaptation
• Joint Contrastive Learning for Unsupervised Domain Adaptation
• Multi-Source EEG Emotion Recognition via Dynamic Contrastive Domain Adaptation
• RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
• AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation
• Similarity-preserving Image-image Domain Adaptation for Person Re-identification
• Open Set Domain Adaptation by Backpropagation
• Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation
• Selecting Data Augmentation for Simulating Interventions
• Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization
• Cluster Alignment with a Teacher for Unsupervised Domain Adaptation
• Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation
• Towards Principled Unsupervised Learning
• Causal Generative Domain Adaptation Networks
• Importance Weighted Adversarial Nets for Partial Domain Adaptation
• Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation
• Transferable Calibration with Lower Bias and Variance in Domain Adaptation
• DiDA: Disentangled Synthesis for Domain Adaptation
• Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation
• Rethink Maximum Mean Discrepancy for Domain Adaptation
• Understanding Self-Training for Gradual Domain Adaptation
• Cross-domain Detection via Graph-induced Prototype Alignment
• A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification
• Iterative self-transfer learning: A general methodology for response time-history prediction based on small dataset
• Regularizing Proxies with Multi-Adversarial Training for Unsupervised Domain-Adaptive Semantic Segmentation
• Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
• Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
• Developing Personalized Models of Blood Pressure Estimation from Wearable Sensors Data Using Minimally-trained Domain Adversarial Neural Networks
• Anatomy-guided domain adaptation for 3D in-bed human pose estimation
• Domain Adaptive Relational Reasoning for 3D Multi-Organ Segmentation
• Correlation Alignment by Riemannian Metric for Domain Adaptation
• Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
• Wasserstein Distance Based Domain Adaptation for Object Detection
• Source Free Unsupervised Graph Domain Adaptation
• Dual Mixup Regularized Learning for Adversarial Domain Adaptation
• Synthetic to Real Adaptation with Generative Correlation Alignment Networks
• Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption
• LiDARNet: A Boundary-Aware Domain Adaptation Model for Point Cloud Semantic Segmentation
• MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation
• Mutual Learning Network for Multi-Source Domain Adaptation
• Entropy Minimization vs. Diversity Maximization for Domain Adaptation
• Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning
• Modified Distribution Alignment for Domain Adaptation with Pre-trained Inception ResNet
• Progressive Domain Expansion Network for Single Domain Generalization
• Attention Regularized Laplace Graph for Domain Adaptation
• Discriminative and Geometry Aware Unsupervised Domain Adaptation
• A Multi-task Deep Network for Person Re-identification
• Data-Driven Clustering via Parameterized Lloyd's Families
• Unifying Unsupervised Domain Adaptation and Zero-Shot Visual Recognition
• Simulations of Common Unsupervised Domain Adaptation Algorithms for Image Classification
• EllSeg-Gen, towards Domain Generalization for head-mounted eyetracking
• ConDA: Continual Unsupervised Domain Adaptation
• Learning Factorized Representations for Open-set Domain Adaptation
• Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification
• Conditional out-of-sample generation for unpaired data using trVAE
• Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
• Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation
• Network Architecture Search for Domain Adaptation
• Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation
• Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation
• Aspect-augmented Adversarial Networks for Domain Adaptation
• Dynamic Weighted Learning for Unsupervised Domain Adaptation
• Domain Alignment with Triplets
• Multi-Task Domain Adaptation for Deep Learning of Instance Grasping from Simulation
• Multi-level Domain Adaptive learning for Cross-Domain Detection
• Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling
• Exploiting Domain Transferability for Collaborative Inter-level Domain Adaptive Object Detection
• Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation
• Discriminative Label Consistent Domain Adaptation
• Improving Compound Activity Classification via Deep Transfer and Representation Learning
• Cross-Domain Visual Recognition via Domain Adaptive Dictionary Learning
• DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification
• Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding
• Gradient Regularized Contrastive Learning for Continual Domain Adaptation
• Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training
• Associative Partial Domain Adaptation
• VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data
• Dual Adversarial Domain Adaptation
• Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
• Domain Adaptation from Synthesis to Reality in Single-model Detector for Video Smoke Detection
• TKD: Temporal Knowledge Distillation for Active Perception
• A Unified Joint Maximum Mean Discrepancy for Domain Adaptation
• Adversarial Domain Adaptation with Domain Mixup
• Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification
• Known-class Aware Self-ensemble for Open Set Domain Adaptation
• DAMIA: Leveraging Domain Adaptation as a Defense against Membership Inference Attacks
• AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
• Unsupervised domain adaptation in brain lesion segmentation with adversarial networks
• Benchmarking the Robustness of Instance Segmentation Models
• Attending to Discriminative Certainty for Domain Adaptation
• Improving Robustness of Deep Learning Based Knee MRI Segmentation: Mixup and Adversarial Domain Adaptation
• Causally motivated Shortcut Removal Using Auxiliary Labels
• Multi-Objective Meta Learning
• Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation
• Domain Adaptation with Auxiliary Target Domain-Oriented Classifier
• Fine-grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach
• Style Normalization and Restitution for Domain Generalization and Adaptation
• On Universal Black-Box Domain Adaptation
• A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes
• Learning Cross-domain Generalizable Features by Representation Disentanglement
• Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests
• Deep causal representation learning for unsupervised domain adaptation
• Class-imbalanced Domain Adaptation: An Empirical Odyssey
• Beyond Fine Tuning: A Modular Approach to Learning on Small Data
• SOSELETO: A Unified Approach to Transfer Learning and Training with Noisy Labels
• Data Augmentation with norm-VAE for Unsupervised Domain Adaptation
• Deep Adversarial Transition Learning using Cross-Grafted Generative Stacks
• Maximum Mean Discrepancy for Generalization in the Presence of Distribution and Missingness Shift
• Adversarial-Learned Loss for Domain Adaptation
• Adaptation Across Extreme Variations using Unlabeled Domain Bridges
• Curriculum based Dropout Discriminator for Domain Adaptation
• HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation
• DINE: Domain Adaptation from Single and Multiple Black-box Predictors
• Joint Feature Distribution Alignment Learning for NIR-VIS and VIS-VIS Face Recognition
• Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising
• Self-reinforcing Unsupervised Matching
• Learning to Match Distributions for Domain Adaptation
• Learning Disentangled Representations for Time Series
• Data Efficient Unsupervised Domain Adaptation for Cross-Modality Image Segmentation
• MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
• Between-Domain Instance Transition Via the Process of Gibbs Sampling in RBM
• Domain-Adaptive Few-Shot Learning
• Generalized Zero and Few-Shot Transfer for Facial Forgery Detection
• Domain Generalization via Semi-supervised Meta Learning
• Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
• Adversarial Attribute-Image Person Re-identification
• Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation
• Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment
• Beyond Domain Adaptation: Unseen Domain Encapsulation via Universal Non-volume Preserving Models
• Discriminative Adversarial Domain Adaptation
• Selective Transfer with Reinforced Transfer Network for Partial Domain Adaptation
• Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning
• Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration
• I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
• Stretching Domain Adaptation: How far is too far?
• Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation
• Cross-Entropy Adversarial View Adaptation for Person Re-identification
• An Extended Framework for Marginalized Domain Adaptation
• Domain-Specific Suppression for Adaptive Object Detection
• Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
• Reinforcement Learning with Videos: Combining Offline Observations with Interaction
• A Cross-Level Information Transmission Network for Predicting Phenotype from New Genotype: Application to Cancer Precision Medicine
• Factorized Adversarial Networks for Unsupervised Domain Adaptation
• Self-training Avoids Using Spurious Features Under Domain Shift
• Privacy-preserving Transfer Learning via Secure Maximum Mean Discrepancy
• Towards Backward-Compatible Representation Learning
• A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
• Deep Domain Adaptation by Geodesic Distance Minimization
• Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment
• Domain Adaptation with Randomized Expectation Maximization
• Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering
• Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
• Joint Semantic Domain Alignment and Target Classifier Learning for Unsupervised Domain Adaptation
• Learning to Transfer for Traffic Forecasting via Multi-task Learning
• Leveraging Systematic Knowledge of 2D Transformations
• Moment-Based Domain Adaptation: Learning Bounds and Algorithms
• DALI: Domain Adaptive LiDAR Object Detection via Distribution-level and Instance-level Pseudo Label Denoising
• Deeply Aligned Adaptation for Cross-domain Object Detection
• Single Domain Dynamic Generalization for Iris Presentation Attack Detection
• Context-Aware Domain Adaptation in Semantic Segmentation
• DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation
• Domain Confusion with Self Ensembling for Unsupervised Adaptation
• Multi-Source Domain Adaptation with Mixture of Experts
• JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting
• Federated Multi-Target Domain Adaptation
• Cycle-consistent Conditional Adversarial Transfer Networks
• Intelligent Icing Detection Model of Wind Turbine Blades Based on SCADA data
• MR Acquisition-Invariant Representation Learning
• Unsupervised Domain Adaptation for Spatio-Temporal Action Localization
• CODE-AE: A Coherent De-confounding Autoencoder for Predicting Patient-Specific Drug Response From Cell Line Transcriptomics
• Cross-Domain Adversarial Auto-Encoder
• A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation
• Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction
• Cost-Effective Training of Deep CNNs with Active Model Adaptation
• Locality Preserving Joint Transfer for Domain Adaptation
• Principled Hybrids of Generative and Discriminative Domain Adaptation
• Improving Unsupervised Domain Adaptation by Reducing Bi-level Feature Redundancy
• Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Domain Adaptation Meets Disentangled Representation Learning and Style Transfer
• Hidden Covariate Shift: A Minimal Assumption For Domain Adaptation
• Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection
• Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach
• Domain-Adversarial and Conditional State Space Model for Imitation Learning
• Robustified Domain Adaptation
• Learning a Domain Classifier Bank for Unsupervised Adaptive Object Detection
• Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation
• Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits
• Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild
• Unsupervised Transductive Domain Adaptation
• Representation Transfer by Optimal Transport
• Causality-inspired Single-source Domain Generalization for Medical Image Segmentation
• Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
• AutoAdapt: Automated Segmentation Network Search for Unsupervised Domain Adaptation
• Transferable Time-Series Forecasting under Causal Conditional Shift
• Mitigating the Impact of Speech Recognition Errors on Chatbot using Sequence-to-Sequence Model
• Structural Regularization
• Learning Domain Adaptive Features with Unlabeled Domain Bridges
• Self-adaptive Re-weighted Adversarial Domain Adaptation
• Domain Conditioned Adaptation Network
• Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation
• Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation
• Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis Transfer
• Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification
• Domain-Invariant Feature Distillation for Cross-Domain Sentiment Classification
• Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification
• Multi-source Few-shot Domain Adaptation
• Transporting Causal Mechanisms for Unsupervised Domain Adaptation
• Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks
• Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation
• Learning from Synthetic Data for Opinion-free Blind Image Quality Assessment in the Wild
• Cross-domain Imitation from Observations
• OmniPrint: A Configurable Printed Character Synthesizer
• Sequential Learning for Domain Generalization
• SODA: Detecting Covid-19 in Chest X-rays with Semi-supervised Open Set Domain Adaptation
• StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching
• Disentanglement Then Reconstruction: Learning Compact Features for Unsupervised Domain Adaptation
• Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation
• Unsupervised domain adaptation via double classifiers based on high confidence pseudo label
• Tackling Imbalanced Data in Cybersecurity with Transfer Learning: A Case with ROP Payload Detection
• Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
• Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation
• Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations
• Learning from Synthetic Animals
• Air-Writing Translater: A Novel Unsupervised Domain Adaptation Method for Inertia-Trajectory Translation of In-air Handwriting
• Attention-Aware Age-Agnostic Visual Place Recognition
• MULE: Multimodal Universal Language Embedding
• Domain Impression: A Source Data Free Domain Adaptation Method
• Differentiated Backprojection Domain Deep Learning for Conebeam Artifact Removal
• Impact of ImageNet Model Selection on Domain Adaptation
• Multimodal Deep Domain Adaptation
• Visual Domain Adaptation with Manifold Embedded Distribution Alignment
• Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
• Parameter Transfer Unit for Deep Neural Networks
• Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks
• Discriminative Clustering for Robust Unsupervised Domain Adaptation
• Image Alignment in Unseen Domains via Domain Deep Generalization
• Stable Distribution Alignment Using the Dual of the Adversarial Distance
• Learning Invariant Representations across Domains and Tasks
• Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain Adaptation
• Matching Embeddings for Domain Adaptation
• Adversarial Feature Training for Generalizable Robotic Visuomotor Control
• Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network
• Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
• Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images
• Range Adaptation for 3D Object Detection in LiDAR
• Adversarial Learning for Zero-shot Domain Adaptation
• Deep Transfer Learning for Cross-domain Activity Recognition
• Against Adversarial Learning: Naturally Distinguish Known and Unknown in Open Set Domain Adaptation
• Unveiling Class-Labeling Structure for Universal Domain Adaptation
• Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptation
• Learning Condensed and Aligned Features for Unsupervised Domain Adaptation Using Label Propagation
• Online Continual Adaptation with Active Self-Training
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• Semi-Supervised Adversarial Discriminative Domain Adaptation
• Self-Supervised Dynamic Networks for Covariate Shift Robustness
• Unsupervised Deep Domain Adaptation for Pedestrian Detection
• Unsupervised Domain Expansion for Visual Categorization
• Divergence Optimization for Noisy Universal Domain Adaptation
• Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
• On the Robustness of Domain Adaption to Adversarial Attacks
• Discriminative Noise Robust Sparse Orthogonal Label Regression-based Domain Adaptation
• Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
• Unsupervised Domain Adaptation Network with Category-Centric Prototype Aligner for Biomedical Image Segmentation
• Learning an Invariant Hilbert Space for Domain Adaptation
• Open-Set Crowdsourcing using Multiple-Source Transfer Learning
• Fighting Copycat Agents in Behavioral Cloning from Observation Histories
• Multifaceted Analysis of Fine-Tuning in Deep Model for Visual Recognition
• Attract or Distract: Exploit the Margin of Open Set
• A Dictionary Approach to Domain-Invariant Learning in Deep Networks
• Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
• Transducer Adaptive Ultrasound Volume Reconstruction
• DWMD: Dimensional Weighted Orderwise Moment Discrepancy for Domain-specific Hidden Representation Matching
• Domain Adaptation for Rare Classes Augmented with Synthetic Samples
• Deep Least Squares Alignment for Unsupervised Domain Adaptation
• Towards Data-Free Domain Generalization
• Deep Doubly Supervised Transfer Network for Diagnosis of Breast Cancer with Imbalanced Ultrasound Imaging Modalities
• Weight Friction: A Simple Method to Overcome Catastrophic Forgetting and Enable Continual Learning
• Appearance invariance in convolutional networks with neighborhood similarity
• From Real to Synthetic and Back: Synthesizing Training Data for Multi-Person Scene Understanding
• Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neuroscience
• Open Set Domain Adaptation for Image and Action Recognition
• Adversarial Domain Randomization
• Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight
• Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation
• Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification
• Enhanced Separable Disentanglement for Unsupervised Domain Adaptation
• Adversarial Transfer Learning for Cross-domain Visual Recognition
• Parameter Reference Loss for Unsupervised Domain Adaptation
• Cross-domain error minimization for unsupervised domain adaptation
• Exploring Dropout Discriminator for Domain Adaptation
• Syn2Real: Forgery Classification via Unsupervised Domain Adaptation
• Zero-Round Active Learning
• Towards Visual Feature Translation
• Topics to Avoid: Demoting Latent Confounds in Text Classification
• Distributionally Robust Language Modeling
• Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark
• Domain Adaptation for Real-World Single View 3D Reconstruction
• Multi-component Image Translation for Deep Domain Generalization
• Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic Adaptation
• Wasserstein Distance Guided Cross-Domain Learning
• Domain Generalization via Universal Non-volume Preserving Models
• Towards Fair Cross-Domain Adaptation via Generative Learning
• Contrastive Domain Adaptation for Question Answering using Limited Text Corpora
• Ensemble Multi-Source Domain Adaptation with Pseudolabels
• On-target Adaptation
• Domain Adaptation by Maximizing Population Correlation with Neural Architecture Search
• Hard Class Rectification for Domain Adaptation
• Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement
• All-Weather Object Recognition Using Radar and Infrared Sensing
• Mixed Set Domain Adaptation
• Learning to see across Domains and Modalities
• Task Guided Compositional Representation Learning for ZDA
• Deep Adversarial Domain Adaptation Based on Multi-layer Joint Kernelized Distance
• One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network
• Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching
• Agile Domain Adaptation
• Deep Spherical Manifold Gaussian Kernel for Unsupervised Domain Adaptation
• Evaluation of Deep Neural Network Domain Adaptation Techniques for Image Recognition
• Universal Multi-Source Domain Adaptation
• SS-CADA: A Semi-Supervised Cross-Anatomy Domain Adaptation for Coronary Artery Segmentation
• Dirty Pixels: Towards End-to-End Image Processing and Perception