mlsanityData to 7 Oct 2026

Spectral Unsupervised Domain Adaptation for Visual Recognition

arXiv 2106.06112 ↗First posted 11 Jun 2021cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Though unsupervised domain adaptation (UDA) has achieved very impressive progress recently, it remains a great challenge due to missing target annotations and the rich discrepancy between source and target distributions. We propose Spectral UDA (SUDA), an effective and efficient UDA technique that works in the spectral space and can generalize across different visual recognition tasks. SUDA addresses the UDA challenges from two perspectives. First, it introduces a spectrum transformer (ST) that mitigates inter-domain discrepancies by enhancing domain-invariant spectra while suppressing domain-variant spectra of source and target samples simultaneously. Second, it introduces multi-view spectral learning that learns useful unsupervised representations by maximizing mutual information among multiple ST-generated spectral views of each target sample. Extensive experiments show that SUDA achieves superior accuracy consistently across different visual tasks in object detection, semantic segmentation and image classification. Additionally, SUDA also works with the transformer-based network and achieves state-of-the-art performance on object detection.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 86 of its 113 references that are in the map. First posted on arXiv 11 Jun 2021.

Builds on

86 of 113 references.

References · 86

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  7. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  8. 2020End-to-End Object Detection with Transformerscited by 7,384
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  10. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  11. 2017Squeeze-and-Excitation Networkscited by 4,763
  12. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
38 more
  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2014Going Deeper with Convolutionscited by 4,231
  3. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  7. 2015Fast R-CNNcited by 2,930
  8. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  9. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  10. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  11. 2017Non-local Neural Networkscited by 2,290
  12. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  13. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  14. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  15. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  16. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  17. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  18. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  19. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  20. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  21. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  22. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  23. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  24. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 572
  25. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  26. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
  27. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  28. 2019Confidence Regularized Self-Trainingcited by 418
  29. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  30. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  31. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  32. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  33. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  34. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  35. 2021A Fourier-based Framework for Domain Generalizationcited by 287
  36. 2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 278
  37. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 269
  38. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 8; 2023: 13; 2024: 10; 2025: 5; 2026: 2.

40 papers.

Sort:

By area:

  1. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  2. 2021A Survey of Unsupervised Domain Adaptation for Visual Recognitioncited by 31
  3. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  4. 2023ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalizationcited by 28
  5. 2023Frequency Domain-based Dataset Distillationcited by 28
  6. 2024EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognitioncited by 23
  7. 2022Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspectivecited by 21
  8. 2024Historical Test-time Prompt Tuning for Vision Foundation Modelscited by 21
  9. 2023Learning to Distill Global Representation for Sparse-View CTcited by 14
  10. 2023Unsupervised Domain Adaption with Pixel-level Discriminator for Image-aware Layout Generationcited by 13
  11. 2023Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memorycited by 11
  12. 2023Order-preserving Consistency Regularization for Domain Adaptation and Generalizationcited by 11
28 more
  1. 2024Vision transformers in domain adaptation and domain generalization: a study of robustnesscited by 11
  2. 2024Open-Vocabulary Object Detection via Language Hierarchycited by 10
  3. 2022UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibrationcited by 8
  4. 2024Low Saturation Confidence Distribution-based Test-Time Adaptation for Cross-Domain Remote Sensing Image Classificationcited by 6
  5. 2025Simulations of Common Unsupervised Domain Adaptation Algorithms for Image Classificationcited by 6
  6. 2024Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaborationcited by 5
  7. 2022Modeling Hierarchical Structural Distance for Unsupervised Domain Adaptationcited by 3
  8. 2022Maximizing Conditional Independence for Unsupervised Domain Adaptationcited by 2
  9. 2022Unsupervised Domain Adaptive Fundus Image Segmentation with Few Labeled Source Datacited by 2
  10. 2022Explaining Cross-Domain Recognition with Interpretable Deep Classifiercited by 2
  11. 2024Fully Test-Time Adaptation for Monocular 3D Object Detectioncited by 2
  12. 2022Beyond Deterministic Translation for Unsupervised Domain Adaptationcited by 1
  13. 2023Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptationcited by 1
  14. 2023DDAM-PS: Diligent Domain Adaptive Mixer for Person Searchcited by 1
  15. 2023GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gapcited by 1
  16. 2024EventDance++: Language-guided Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognitioncited by 1
  17. 2025Noise Optimized Conditional Diffusion for Domain Adaptationcited by 1
  18. 2022IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labelscited by 0
  19. 2023Crucial Semantic Classifier-based Adversarial Learning for Unsupervised Domain Adaptationcited by 0
  20. 2023Diffusion-based Target Sampler for Unsupervised Domain Adaptationcited by 0
  21. 2023Maximizing Information in Domain-Invariant Representation Improves Transfer Learningcited by 0
  22. 2024Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approachcited by 0
  23. 2024Vox-UDA: Voxel-wise Unsupervised Domain Adaptation for Cryo-Electron Subtomogram Segmentation with Denoised Pseudo Labelingcited by 0
  24. 2025Domain Adaptive Skin Lesion Classification via Conformal Ensemble of Vision Transformerscited by 0
  25. 2025UniDet-D: A Unified Dynamic Spectral Attention Model for Object Detection under Adverse Weatherscited by 0
  26. 2025Global Variational Inference Enhanced Robust Domain Adaptationcited by 0
  27. 2026GAN-based Domain Adaptation for Image-aware Layout Generation in Advertising Poster Designcited by 0
  28. 2026Domain-Division based Progressive Learning for Source-Free Domain Adaptationcited by 0