mlsanityData to 14 Oct 2026

OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation

arXiv 2205.10738 ↗First posted 22 May 2022cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Unsupervised domain adaptation is one of the challenging problems in computer vision. This paper presents a novel approach to unsupervised domain adaptations based on the optimal transport-based distance. Our approach allows aligning target and source domains without the requirement of meaningful metrics across domains. In addition, the proposal can associate the correct mapping between source and target domains and guarantee a constraint of topology between source and target domains. The proposed method is evaluated on different datasets in various problems, i.e. (i) digit recognition on MNIST, MNIST-M, USPS datasets, (ii) Object recognition on Amazon, Webcam, DSLR, and VisDA datasets, (iii) Insect Recognition on the IP102 dataset. The experimental results show that our proposed method consistently improves performance accuracy. Also, our framework could be incorporated with any other CNN frameworks within an end-to-end deep network design for recognition problems to improve their performance.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 35 of its 55 references that are in the map. First posted on arXiv 22 May 2022.

Builds on

35 of 55 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  5. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  6. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  7. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
  8. 2015Optimal Transport for Domain Adaptationcited by 463
  9. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  10. 2017VisDA: The Visual Domain Adaptation Challengecited by 435
  11. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 282
  12. 2016Coupled Generative Adversarial Networkscited by 216
23 more
  1. 2019Generalized Sliced Wasserstein Distancescited by 208
  2. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 206
  3. 2017Image to Image Translation for Domain Adaptationcited by 171
  4. 2018Generative Modeling using the Sliced Wasserstein Distancecited by 108
  5. 2018Optimal Transport for Multi-source Domain Adaptation under Target Shiftcited by 68
  6. 2019Sliced Gromov-Wassersteincited by 66
  7. 2019Learning Generative Models across Incomparable Spacescited by 53
  8. 2020Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognitioncited by 36
  9. 2021Progressive Semantic Segmentationcited by 35
  10. 2021The Right to Talk: An Audio-Visual Transformer Approachcited by 33
  11. 2021DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Trackingcited by 31
  12. 2021BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentationcited by 31
  13. 2022DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognitioncited by 31
  14. 2013Efficient Learning of Domain-invariant Image Representationscited by 20
  15. 2017Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentationcited by 16
  16. 2018Automatic Face Aging in Videos via Deep Reinforcement Learningcited by 16
  17. 2017Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognitioncited by 15
  18. 2016Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machinescited by 10
  19. 2019Fast Flow Reconstruction via Robust Invertible nxn Convolutioncited by 6
  20. 2016Deep Appearance Models: A Deep Boltzmann Machine Approach for Face Modelingcited by 5
  21. 2018Feature Transfer Learning for Deep Face Recognition with Under-Represented Datacited by 4
  22. 2021Relaxed Conditional Image Transfer for Semi-supervised Domain Adaptationcited by 2
  23. 2020Domain Adaptation in Highly Imbalanced and Overlapping Datasetscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 4; 2025: 3; 2026: 1.

12 papers.

  1. 2023Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understandingcited by 29
  2. 2023FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understandingcited by 27
  3. 2023Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspectivecited by 14
  4. 2023FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understandingcited by 13
  5. 2024BRACTIVE: A Brain Activation Approach to Human Visual Brain Learningcited by 6
  6. 2025MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learningcited by 3
  7. 2024FLAASH: Flow-Attention Adaptive Semantic Hierarchical Fusion for Multi-Modal Tobacco Content Analysiscited by 2
  8. 2024Public Health Advocacy Dataset: A Dataset of Tobacco Usage Videos from Social Mediacited by 2
  9. 2025CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identificationcited by 2
  10. 2024CarcassFormer: An End-to-end Transformer-based Framework for Simultaneous Localization, Segmentation and Classification of Poultry Carcass Defectcited by 1
  11. 2026OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materialscited by 1
  12. 2025BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understandingcited by 0