Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation (2404.10322v1)

Published 16 Apr 2024 in cs.CV

Abstract: Few-shot semantic segmentation (FSS) has achieved great success on segmenting objects of novel classes, supported by only a few annotated samples. However, existing FSS methods often underperform in the presence of domain shifts, especially when encountering new domain styles that are unseen during training. It is suboptimal to directly adapt or generalize the entire model to new domains in the few-shot scenario. Instead, our key idea is to adapt a small adapter for rectifying diverse target domain styles to the source domain. Consequently, the rectified target domain features can fittingly benefit from the well-optimized source domain segmentation model, which is intently trained on sufficient source domain data. Training domain-rectifying adapter requires sufficiently diverse target domains. We thus propose a novel local-global style perturbation method to simulate diverse potential target domains by perturbating the feature channel statistics of the individual images and collective statistics of the entire source domain, respectively. Additionally, we propose a cyclic domain alignment module to facilitate the adapter effectively rectifying domains using a reverse domain rectification supervision. The adapter is trained to rectify the image features from diverse synthesized target domains to align with the source domain. During testing on target domains, we start by rectifying the image features and then conduct few-shot segmentation on the domain-rectified features. Extensive experiments demonstrate the effectiveness of our method, achieving promising results on cross-domain few-shot semantic segmentation tasks. Our code is available at https://github.com/Matt-Su/DR-Adapter.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (59)
  1. Large-scale interactive object segmentation with human annotators. In CVPR, 2019.
  2. Few-shot segmentation without meta-learning: A good transductive inference is all you need? In CVPR, 2021.
  3. Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE Transactions on Medical Imaging, 2013.
  4. Domain generalization by solving jigsaw puzzles. In CVPR, 2019.
  5. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. Transactions on Pattern Analysis and Machine Intelligence, 2017.
  6. Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368, 2019.
  7. Deepglobe 2018: A challenge to parse the earth through satellite images. In CVPR, 2018.
  8. Few-shot semantic segmentation with prototype learning. In BMVC, 2018.
  9. Learning to learn with variational information bottleneck for domain generalization. In ECCV, 2020.
  10. The pascal visual object classes (voc) challenge. IJCV, 2010.
  11. Few-shot object detection with attention-rpn and multi-relation detector. In CVPR, 2020.
  12. Self-support few-shot semantic segmentation. In ECCV, 2022a.
  13. Towards robust object detection invariant to real-world domain shifts. In ICLR, 2022b.
  14. Domain generalization for object recognition with multi-task autoencoders. In ICCV, 2015.
  15. Semantic contours from inverse detectors. In ICCV, 2011.
  16. Arbitrary style transfer in real-time with adaptive instance normalization. In CVPR, 2017.
  17. Restnet: Boosting cross-domain few-shot segmentation with residual transformation network. In BMVC, 2023.
  18. Automatic tuberculosis screening using chest radiographs. IEEE Transactions on Medical Imaging, 2013.
  19. Segment anything. In ICCV, 2023.
  20. Cross-domain few-shot semantic segmentation. In ECCV, 2022.
  21. Adaptive prototype learning and allocation for few-shot segmentation. In CVPR, 2021.
  22. Fss-1000: A 1000-class dataset for few-shot segmentation. In CVPR, 2020.
  23. Uncertainty modeling for out-of-distribution generalization. In ICLR, 2022.
  24. Microsoft coco: Common objects in context. In ECCV, 2014.
  25. Feature transformation ensemble model with batch spectral regularization for cross-domain few-shot classification. arXiv preprint arXiv:2005.08463, 2020a.
  26. Dynamic extension nets for few-shot semantic segmentation. In ACMMM, 2020b.
  27. Crnet: Cross-reference networks for few-shot segmentation. In CVPR, 2020c.
  28. Part-aware prototype network for few-shot semantic segmentation. In ECCV, 2020d.
  29. Learning non-target knowledge for few-shot semantic segmentation. In CVPR, 2022.
  30. Fully convolutional networks for semantic segmentation. In CVPR, 2015.
  31. Simpler is better: Few-shot semantic segmentation with classifier weight transformer. In ICCV, 2021.
  32. Hypercorrelation squeeze for few-shot segmentation. In ICCV, 2021.
  33. Unified deep supervised domain adaptation and generalization. In ICCV, 2017.
  34. Feature weighting and boosting for few-shot segmentation. In ICCV, 2019.
  35. Hierarchical dense correlation distillation for few-shot segmentation. In CVPR, 2023.
  36. U-net: Convolutional networks for biomedical image segmentation. In MICCAI, 2015.
  37. Tune it the right way: Unsupervised validation of domain adaptation via soft neighborhood density. In ICCV, 2021.
  38. Generalizing across domains via cross-gradient training. ICLR, 2018.
  39. Dense cross-query-and-support attention weighted mask aggregation for few-shot segmentation. In ECCV, 2022.
  40. Prototypical networks for few-shot learning. NeurIPS, 2017.
  41. Prior guided feature enrichment network for few-shot segmentation. TPAMI, 2020.
  42. The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data, 2018.
  43. Matching networks for one shot learning. NeurIPS, 2016.
  44. Generalizing to unseen domains via adversarial data augmentation. NeurIPS, 2018.
  45. Learning robust representations by projecting superficial statistics out. In ICLR, 2019a.
  46. Panet: Few-shot image semantic segmentation with prototype alignment. In ICCV, 2019b.
  47. Remember the difference: Cross-domain few-shot semantic segmentation via meta-memory transfer. In CVPR, 2022.
  48. Prototype mixture models for few-shot semantic segmentation. In ECCV, 2020.
  49. Mining latent classes for few-shot segmentation. In ICCV, 2021.
  50. Prototypical cross-domain self-supervised learning for few-shot unsupervised domain adaptation. In CVPR, 2021.
  51. Self-guided and cross-guided learning for few-shot segmentation. In CVPR, 2021a.
  52. Pyramid graph networks with connection attentions for region-based one-shot semantic segmentation. In ICCV, 2019a.
  53. Canet: Class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In CVPR, 2019b.
  54. Few-shot segmentation via cycle-consistent transformer. NeurIPS, 2021b.
  55. Feature-proxy transformer for few-shot segmentation. NeurIPS, 2022.
  56. Personalize segment anything model with one shot. arXiv preprint arXiv:2305.03048, 2023.
  57. Sg-one: Similarity guidance network for one-shot semantic segmentation. Transactions on Cybernetics, 2020.
  58. Learning to generate novel domains for domain generalization. In ECCV, 2020.
  59. Domain generalization with mixstyle. In ICLR, 2021.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now