Conditional Adversarial Domain Adaptation

Abstract

Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may not effectively align different domains of multimodal distributions native in classification problems. In this paper, we present conditional adversarial domain adaptation, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions. Conditional domain adversarial networks (CDANs) are designed with two novel conditioning strategies: multilinear conditioning that captures the cross-covariance between feature representations and classifier predictions to improve the discriminability, and entropy conditioning that controls the uncertainty of classifier predictions to guarantee the transferability. With theoretical guarantees and a few lines of codes, the approach has exceeded state-of-the-art results on five datasets.

32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada

Cited by in corpus (336)

• Deep Subdomain Adaptation Network for Image Classification
• Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study
• Model Adaptation: Unsupervised Domain Adaptation without Source Data
• Maximum Density Divergence for Domain Adaptation
• Learning Robust Global Representations by Penalizing Local Predictive Power
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Out-of-Distribution Generalization via Risk Extrapolation (REx)
• Bridging Theory and Algorithm for Domain Adaptation
• A Comprehensive Survey on Transfer Learning
• Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
• Deep Residual Correction Network for Partial Domain Adaptation
• Universal Domain Adaptation through Self Supervision
• Self-supervised Domain Adaptation for Computer Vision Tasks
• Federated Adversarial Domain Adaptation
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
• Learning Disentangled Semantic Representation for Domain Adaptation
• Improve Unsupervised Domain Adaptation with Mixup Training
• Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain
• CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
• Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
• Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice
• Integrating Expert Knowledge with Domain Adaptation for Unsupervised Fault Diagnosis
• Unsupervised Domain Adaptation via Discriminative Manifold Propagation
• The Risks of Invariant Risk Minimization
• Self-supervised Autoregressive Domain Adaptation for Time Series Data
• HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
• Semi-supervised Domain Adaptation via Minimax Entropy
• Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
• Missing-Class-Robust Domain Adaptation by Unilateral Alignment for Fault Diagnosis
• Generalized Domain Conditioned Adaptation Network
• Domain Generalization via Optimal Transport with Metric Similarity Learning
• Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
• Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation
• Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
• Cycle Self-Training for Domain Adaptation
• TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimation
• Unsupervised Object Segmentation by Redrawing
• Learning Transferable Parameters for Unsupervised Domain Adaptation
• Dynamic Instance Domain Adaptation
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Learning Causal Semantic Representation for Out-of-Distribution Prediction
• Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation
• Model Patching: Closing the Subgroup Performance Gap with Data Augmentation
• Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection
• Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation
• Adversarial Domain Adaptation with Prototype-Based Normalized Output Conditioner
• KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
• Multi-adversarial Faster-RCNN for Unrestricted Object Detection
• Driving Behavior Explanation with Multi-level Fusion
• Domain-Symmetric Networks for Adversarial Domain Adaptation
• Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets
• Unsupervised Domain Adaptation with Progressive Adaptation of Subspaces
• A Survey on Deep Transfer Learning
• Unsupervised Domain Adaptation of Black-Box Source Models
• Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories
• Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation
• Rethinking Distributional Matching Based Domain Adaptation
• Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
• Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels
• Confidence Regularized Self-Training
• Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation
• Dual adversarial and contrastive network for single-source domain generalization in fault diagnosis
• Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection
• Source Free Domain Adaptation with Image Translation
• Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay
• Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics
• Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol
• Decoupled Adaptation for Cross-Domain Object Detection
• Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results
• Robust Local Preserving and Global Aligning Network for Adversarial Domain Adaptation
• Domain-Specific Batch Normalization for Unsupervised Domain Adaptation
• Minimum Class Confusion for Versatile Domain Adaptation
• Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains
• Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations
• A Prototype-Oriented Framework for Unsupervised Domain Adaptation
• Domain Adaptation without Source Data
• TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation
• Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
• Test-time Batch Statistics Calibration for Covariate Shift
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Harmonizing Transferability and Discriminability for Adapting Object Detectors
• Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains
• Semi-supervised representation learning via dual autoencoders for domain adaptation
• Easy Transfer Learning By Exploiting Intra-domain Structures
• SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
• Joint Contrastive Learning for Unsupervised Domain Adaptation
• Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data
• Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation
• Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation
• Transformer-Based Source-Free Domain Adaptation
• Adapting Object Detectors with Conditional Domain Normalization
• Rethink Maximum Mean Discrepancy for Domain Adaptation
• Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation
• Towards Shape Biased Unsupervised Representation Learning for Domain Generalization
• Transferable Calibration with Lower Bias and Variance in Domain Adaptation
• Instance Adaptive Self-Training for Unsupervised Domain Adaptation
• Vicinal and categorical domain adaptation
• Corporate Bankruptcy Prediction with Domain-Adapted BERT
• Cross-domain Detection via Graph-induced Prototype Alignment
• Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation
• Self-training for Few-shot Transfer Across Extreme Task Differences
• Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation
• Prototypical Partial Optimal Transport for Universal Domain Adaptation
• Jointly De-biasing Face Recognition and Demographic Attribute Estimation
• Out-of-distribution Prediction with Invariant Risk Minimization: The Limitation and An Effective Fix
• Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners
• Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
• Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
• TWINs: Two Weighted Inconsistency-reduced Networks for Partial Domain Adaptation
• Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
• Domain Adversarial Training for Accented Speech Recognition
• Cross-domain Contrastive Learning for Unsupervised Domain Adaptation
• Dual Mixup Regularized Learning for Adversarial 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
• Entropy Minimization vs. Diversity Maximization for Domain Adaptation
• Modified Distribution Alignment for Domain Adaptation with Pre-trained Inception ResNet
• Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer
• Mutual Learning Network for Multi-Source Domain Adaptation
• Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning
• ConDA: Continual Unsupervised Domain Adaptation
• Meta-Learning across Meta-Tasks for Few-Shot Learning
• Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
• CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation
• Unifying Unsupervised Domain Adaptation and Zero-Shot Visual Recognition
• Network Architecture Search for Domain Adaptation
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
• Dynamic Weighted Learning for Unsupervised Domain Adaptation
• Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation
• Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling
• Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning
• Physics-Informed Deep Learning and Partial Transfer Learning for Bearing Fault Diagnosis in the Presence of Highly Missing Data
• Domain Alignment with Triplets
• Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach
• Improving Compound Activity Classification via Deep Transfer and Representation Learning
• Environment Inference for Invariant Learning
• VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data
• Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
• Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation
• Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation
• Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation
• Bayesian Uncertainty Matching for Unsupervised Domain Adaptation
• VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation
• Learning from a Complementary-label Source Domain: Theory and Algorithms
• DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification
• Few-Shot Learning as Domain Adaptation: Algorithm and Analysis
• ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
• Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training
• Semantics-Aware Image to Image Translation and Domain Transfer
• Adaptive Domain Generalization via Online Disagreement Minimization
• Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation
• A Theory of Label Propagation for Subpopulation Shift
• Adversarial Domain Adaptation with Domain Mixup
• Domain Adaptation with Auxiliary Target Domain-Oriented Classifier
• Open Domain Generalization with Domain-Augmented Meta-Learning
• Enforcing Predictive Invariance across Structured Biomedical Domains
• Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation
• Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation
• Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation
• Adversarial Cross-Domain Action Recognition with Co-Attention
• Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation
• Attending to Discriminative Certainty for Domain Adaptation
• FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
• Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
• Adversarial-Learned Loss for Domain Adaptation
• Data Augmentation with norm-VAE for Unsupervised Domain Adaptation
• Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters
• IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
• Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation
• ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation
• When Invariant Representation Learning Meets Label Shift: Insufficiency and Theoretical Insights
• SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images
• DINE: Domain Adaptation from Single and Multiple Black-box Predictors
• Deep Adversarial Transition Learning using Cross-Grafted Generative Stacks
• Curriculum based Dropout Discriminator for Domain Adaptation
• Domain-Adaptive Few-Shot Learning
• Continuous Transfer Learning with Label-informed Distribution Alignment
• MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
• Learning to Match Distributions for Domain Adaptation
• Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition
• Learning Smooth Representation for Unsupervised Domain Adaptation
• Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation
• Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Recognition
• Adaptive Object Detection with Dual Multi-Label Prediction
• Domain Generalization via Semi-supervised Meta Learning
• Unsupervised Domain Adaptation by Uncertain Feature Alignment
• SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning
• Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation
• Domain-Specific Suppression for Adaptive Object Detection
• Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders
• Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
• Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
• A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
• Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning
• Discriminative Adversarial Domain Adaptation
• Multi-Stage Transfer Learning with an Application to Selection Process
• A Low-Cost Neural ODE with Depthwise Separable Convolution for Edge Domain Adaptation on FPGAs
• On Evolving Attention Towards Domain Adaptation
• I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
• Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation
• Enhancing ensemble learning and transfer learning in multimodal data analysis by adaptive dimensionality reduction
• Joint Semantic Domain Alignment and Target Classifier Learning for Unsupervised Domain Adaptation
• Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
• AU-Guided Unsupervised Domain Adaptive Facial Expression Recognition
• Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data
• Domain Adaptative Causality Encoder
• On Localized Discrepancy for Domain Adaptation
• Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition
• Cycle-consistent Conditional Adversarial Transfer Networks
• Unsupervised Calibration under Covariate Shift
• Learning to Diversify for Single Domain Generalization
• Adaptive Invariance for Molecule Property Prediction
• Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments
• Unsupervised Domain Adaptation with Progressive Domain Augmentation
• Towards Corruption-Agnostic Robust Domain Adaptation
• Graceful Degradation and Related Fields
• ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation
• Self-adaptive Re-weighted Adversarial Domain Adaptation
• Using Latent Codes for Class Imbalance Problem in Unsupervised Domain Adaptation
• CUDA: Contradistinguisher for Unsupervised Domain Adaptation
• Dynamic Feature Alignment for Semi-supervised Domain Adaptation
• Gradual Domain Adaptation via Self-Training of Auxiliary Models
• Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation
• Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation
• Hidden Covariate Shift: A Minimal Assumption For Domain Adaptation
• Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separation
• Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation
• Visualizing Adapted Knowledge in Domain Transfer
• Adversarial Consistent Learning on Partial Domain Adaptation of PlantCLEF 2020 Challenge
• Improving Unsupervised Domain Adaptation by Reducing Bi-level Feature Redundancy
• Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation
• SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
• Domain Conditioned Adaptation Network
• Improving Model Robustness with Latent Distribution Locally and Globally
• Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
• Domain Adaptive SiamRPN++ for Object Tracking in the Wild
• Contradictory Structure Learning for Semi-supervised Domain Adaptation
• A General Upper Bound for Unsupervised Domain Adaptation
• Disentanglement Then Reconstruction: Learning Compact Features for Unsupervised Domain Adaptation
• Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection
• Transporting Causal Mechanisms for Unsupervised Domain Adaptation
• Adversarial Robustness for Unsupervised Domain Adaptation
• TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
• Unsupervised domain adaptation via double classifiers based on high confidence pseudo label
• Multi-source Few-shot Domain Adaptation
• Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks
• Omni-GAN: On the Secrets of cGANs and Beyond
• Self-Supervised Domain Adaptation with Consistency Training
• Stochastic Adversarial Gradient Embedding for Active Domain Adaptation
• Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
• Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network
• Hypothesis Disparity Regularized Mutual Information Maximization
• Mining Label Distribution Drift in Unsupervised Domain Adaptation
• Domain Impression: A Source Data Free Domain Adaptation Method
• Learning Invariant Representations across Domains and Tasks
• Class Distribution Alignment for Adversarial Domain Adaptation
• Towards Accurate and Robust Domain Adaptation under Noisy Environments
• Discriminative Active Learning for Domain Adaptation
• VideoDG: Generalizing Temporal Relations in Videos to Novel Domains
• Target Consistency for Domain Adaptation: when Robustness meets Transferability
• Unsupervised Domain Adaptation on Reading Comprehension
• Impact of ImageNet Model Selection on Domain Adaptation
• A Style and Semantic Memory Mechanism for Domain Generalization
• 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
• Metric-Learning-Assisted Domain Adaptation
• Sparsely-Labeled Source Assisted Domain Adaptation
• Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation
• Matching Embeddings for Domain Adaptation
• A Dictionary Approach to Domain-Invariant Learning in Deep Networks
• Against Adversarial Learning: Naturally Distinguish Known and Unknown in Open Set Domain Adaptation
• On the Robustness of Domain Adaption to Adversarial Attacks
• DRR4Covid: Learning Automated COVID-19 Infection Segmentation from Digitally Reconstructed Radiographs
• Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation
• Conditional Bures Metric for Domain Adaptation
• Divergence Optimization for Noisy Universal Domain Adaptation
• Unsupervised Domain Adaptation Network with Category-Centric Prototype Aligner for Biomedical Image Segmentation
• Bi-Dimensional Feature Alignment for Cross-Domain Object Detection
• Interventional Domain Adaptation
• Unsupervised Domain Expansion for Visual Categorization
• Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptation
• Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts
• FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation
• PØDA: Prompt-driven Zero-shot Domain Adaptation
• Teacher-Student Domain Adaptation for Biosensor Models
• Fast and Accurate Transferability Measurement for Heterogeneous Multivariate Data
• Multi-Purposing Domain Adaptation Discriminators for Pseudo Labeling Confidence
• Unveiling Class-Labeling Structure for Universal Domain Adaptation
• Online Continual Adaptation with Active Self-Training
• Self-Adaptive Partial Domain Adaptation
• S${}^3$VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation
• NI-UDA: Graph Adversarial Domain Adaptation from Non-shared-and-Imbalanced Big Data to Small Imbalanced Applications
• Deep Domain Adaptation for Pavement Crack Detection
• Domain Agnostic Learning for Unbiased Authentication
• Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering
• Semi-Supervised Domain Generalization with Evolving Intermediate Domain
• One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network
• Deep Adversarial Domain Adaptation Based on Multi-layer Joint Kernelized Distance
• Hard Class Rectification for Domain Adaptation
• Unsupervised Domain Adaptation: A Reality Check
• Cross-Domain Latent Modulation for Variational Transfer Learning
• Universal Multi-Source Domain Adaptation
• Synthetic-to-Real Domain Adaptation for Lane Detection
• How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?
• Robust Ensembling Network for Unsupervised Domain Adaptation
• Teacher-Student Competition for Unsupervised Domain Adaptation
• Cross-domain error minimization for unsupervised domain adaptation
• The Role of Embedding Complexity in Domain-invariant Representations
• Mixed Set Domain Adaptation
• Domain Adaptation with Incomplete Target Domains
• Transferable Semantic Augmentation for Domain Adaptation
• Deep Least Squares Alignment for Unsupervised Domain Adaptation
• Knothe-Rosenblatt transport for Unsupervised Domain Adaptation
• Dynamic Domain Adaptation for Efficient Inference
• Evaluation of Deep Neural Network Domain Adaptation Techniques for Image Recognition
• Semi-Supervised Domain Adaptation via Selective Pseudo Labeling and Progressive Self-Training
• iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection
• Deep Spherical Manifold Gaussian Kernel for Unsupervised Domain Adaptation
• Towards Fair Cross-Domain Adaptation via Generative Learning
• PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python
• Domain Adaptation by Maximizing Population Correlation with Neural Architecture Search
• On-target Adaptation
• MUDAS: Mote-scale Unsupervised Domain Adaptation in Multi-label Sound Classification
• Transferrable Contrastive Learning for Visual Domain Adaptation
• Densely Semantic Enhancement for Domain Adaptive Region-free Detectors
• Exploring Dropout Discriminator for Domain Adaptation
• Frustratingly Easy Uncertainty Estimation for Distribution Shift
• Channel-Temporal Attention for First-Person Video Domain Adaptation
• Importance Filtered Cross-Domain Adaptation
• GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation
• Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment
• Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation
• Domain-Specific Bias Filtering for Single Labeled Domain Generalization