mlsanityData to 7 Oct 2026

Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation

arXiv 1910.05562 ↗First posted 12 Oct 2019cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

Recent works on domain adaptation exploit adversarial training to obtain domain-invariant feature representations from the joint learning of feature extractor and domain discriminator networks. However, domain adversarial methods render suboptimal performances since they attempt to match the distributions among the domains without considering the task at hand. We propose Drop to Adapt (DTA), which leverages adversarial dropout to learn strongly discriminative features by enforcing the cluster assumption. Accordingly, we design objective functions to support robust domain adaptation. We demonstrate efficacy of the proposed method on various experiments and achieve consistent improvements in both image classification and semantic segmentation tasks. Our source code is available at https://github.com/postBG/DTA.pytorch.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 31; 2022: 17; 2023: 6; 2024: 6; 2025: 2.

62 papers.

Sort:

By area:

  1. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
  2. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  3. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  4. 2021Domain Impression: A Source Data Free Domain Adaptation Methodcited by 91
  5. 2021TVT: Transferable Vision Transformer for Unsupervised Domain Adaptationcited by 81
  6. 2023On the Stability-Plasticity Dilemma of Class-Incremental Learningcited by 55
  7. 2021Cross-View Regularization for Domain Adaptive Panoptic Segmentationcited by 41
  8. 2022Gradual Domain Adaptation without Indexed Intermediate Domainscited by 26
  9. 2021Leveraging Self-Supervision for Cross-Domain Crowd Countingcited by 24
  10. 2021Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillationcited by 23
  11. 2021UMAD: Universal Model Adaptation under Domain and Category Shiftcited by 23
  12. 2022DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentationcited by 22
38 more
  1. 2022Unsupervised Continual Semantic Adaptation through Neural Renderingcited by 22
  2. 2023SPA: A Graph Spectral Alignment Perspective for Domain Adaptationcited by 22
  3. 2023DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalizationcited by 21
  4. 2021Discovering Distinctive "Semantics" in Super-Resolution Networkscited by 20
  5. 2021Pareto Domain Adaptationcited by 20
  6. 2021S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptationcited by 19
  7. 2022Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictorscited by 19
  8. 2022Learning Semantic Segmentation from Multiple Datasets with Label Shiftscited by 14
  9. 2022Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptationcited by 14
  10. 2021Divergence Optimization for Noisy Universal Domain Adaptationcited by 13
  11. 2022Unsupervised RGB-to-Thermal Domain Adaptation via Multi-Domain Attention Networkcited by 13
  12. 2021Self-training Guided Adversarial Domain Adaptation For Thermal Imagerycited by 11
  13. 2021Partial Domain Adaptation without Domain Alignmentcited by 11
  14. 2021Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentationcited by 10
  15. 2021A Curriculum-style Self-training Approach for Source-Free Semantic Segmentationcited by 10
  16. 2021An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Trainingcited by 10
  17. 2021Mining Data Impressions from Deep Models as Substitute for the Unavailable Training Datacited by 7
  18. 2024Generalizable Facial Expression Recognitioncited by 6
  19. 2024Low Saturation Confidence Distribution-based Test-Time Adaptation for Cross-Domain Remote Sensing Image Classificationcited by 6
  20. 2021Road Scenes Segmentation Across Different Domains by Disentangling Latent Representationscited by 5
  21. 2022Domain Adaptation with Adversarial Training on Penultimate Activationscited by 5
  22. 2024Efficient unsupervised domain adaptation via self-supervised vision transformer and synergistic cross-domain alignmentcited by 5
  23. 2021Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentationcited by 4
  24. 2021Discriminative Domain-Invariant Adversarial Network for Deep Domain Generalizationcited by 4
  25. 2022Domain Confused Contrastive Learning for Unsupervised Domain Adaptationcited by 4
  26. 2021Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learningcited by 3
  27. 2021Burn After Reading: Online Adaptation for Cross-domain Streaming Datacited by 3
  28. 2021Reciprocal Normalization for Domain Adaptationcited by 3
  29. 2022Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challengescited by 3
  30. 2021Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learningcited by 2
  31. 2021Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptationcited by 2
  32. 2021Multitask Identity-Aware Image Steganography via Minimax Optimizationcited by 2
  33. 2021Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 2
  34. 2022Exploiting Domain Transferability for Collaborative Inter-level Domain Adaptive Object Detectioncited by 2
  35. 2022Adversarial and Random Transformations for Robust Domain Adaptation and Generalizationcited by 2
  36. 2025SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptationcited by 2
  37. 2021Exploring Dropout Discriminator for Domain Adaptationcited by 1
  38. 2021Improving the Generalization of Meta-learning on Unseen Domains via Adversarial Shiftcited by 1

50 most cited of 62 All 62 (JSON)