Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations (2210.14358v3)

Published 25 Oct 2022 in cs.LG and cs.CV

Abstract: There is an inescapable long-tailed class-imbalance issue in many real-world classification problems. Current methods for addressing this problem only consider scenarios where all examples come from the same distribution. However, in many cases, there are multiple domains with distinct class imbalance. We study this multi-domain long-tailed learning problem and aim to produce a model that generalizes well across all classes and domains. Towards that goal, we introduce TALLY, a method that addresses this multi-domain long-tailed learning problem. Built upon a proposed selective balanced sampling strategy, TALLY achieves this by mixing the semantic representation of one example with the domain-associated nuisances of another, producing a new representation for use as data augmentation. To improve the disentanglement of semantic representations, TALLY further utilizes a domain-invariant class prototype that averages out domain-specific effects. We evaluate TALLY on several benchmarks and real-world datasets and find that it consistently outperforms other state-of-the-art methods in both subpopulation and domain shift. Our code and data have been released at https://github.com/huaxiuyao/TALLY.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Invariance principle meets information bottleneck for out-of-distribution generalization. 2021.
  2. Generalizing to unseen domains via distribution matching. arXiv preprint arXiv:1911.00804, 2019.
  3. Invariant risk minimization. arXiv preprint arXiv:1907.02893, 2019.
  4. Recognition in terra incognita. In Proceedings of the European conference on computer vision (ECCV), pp.  456–473, 2018.
  5. The iwildcam 2020 competition dataset. arXiv preprint arXiv:2004.10340, 2020.
  6. Learning imbalanced datasets with label-distribution-aware margin loss. Advances in neural information processing systems, 32, 2019.
  7. Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357, 2002.
  8. Remix: rebalanced mixup. In European Conference on Computer Vision, pp.  95–110. Springer, 2020.
  9. Parametric contrastive learning. In Proceedings of the IEEE/CVF international conference on computer vision, pp.  715–724, 2021.
  10. Class-balanced loss based on effective number of samples. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp.  9268–9277, 2019.
  11. A multiple resampling method for learning from imbalanced data sets. Computational intelligence, 20(1):18–36, 2004.
  12. Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias. In Proceedings of the IEEE International Conference on Computer Vision, pp.  1657–1664, 2013.
  13. In search of lost domain generalization. arXiv preprint arXiv:2007.01434, 2021.
  14. Out-of-distribution prediction with invariant risk minimization: The limitation and an effective fix. arXiv preprint arXiv:2101.07732, 2021.
  15. Disentangling label distribution for long-tailed visual recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  6626–6636, 2021.
  16. Arbitrary style transfer in real-time with adaptive instance normalization. In Proceedings of the IEEE international conference on computer vision, pp.  1501–1510, 2017.
  17. Rethinking class-balanced methods for long-tailed visual recognition from a domain adaptation perspective. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  7610–7619, 2020.
  18. Decoupling representation and classifier for long-tailed recognition. 2020.
  19. On invariance penalties for risk minimization. arXiv preprint arXiv:2106.09777, 2021.
  20. Wilds: A benchmark of in-the-wild distribution shifts. In International Conference on Machine Learning, pp. 5637–5664. PMLR, 2021.
  21. Out-of-distribution generalization via risk extrapolation (rex). In International Conference on Machine Learning, pp. 5815–5826. PMLR, 2021.
  22. Deeper, broader and artier domain generalization. In Proceedings of the IEEE international conference on computer vision, pp.  5542–5550, 2017.
  23. Domain generalization with adversarial feature learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.  5400–5409, 2018.
  24. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pp.  2980–2988, 2017.
  25. Deep representation learning on long-tailed data: A learnable embedding augmentation perspective. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  2970–2979, 2020.
  26. Exploratory undersampling for class-imbalance learning. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 39(2):539–550, 2008.
  27. Moment matching for multi-source domain adaptation. In Proceedings of the IEEE/CVF international conference on computer vision, pp.  1406–1415, 2019.
  28. Model-based domain generalization. Advances in Neural Information Processing Systems, 34:20210–20229, 2021.
  29. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. In ICLR, 2020.
  30. Gradient matching for domain generalization. arXiv preprint arXiv:2104.09937, 2021.
  31. Open domain generalization with domain-augmented meta-learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  9624–9633, 2021.
  32. Deep coral: Correlation alignment for deep domain adaptation. In European conference on computer vision, pp.  443–450. Springer, 2016.
  33. Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022, 2016.
  34. Deep hashing network for unsupervised domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  5018–5027, 2017.
  35. Long-tailed recognition by routing diverse distribution-aware experts. arXiv preprint arXiv:2010.01809, 2020a.
  36. Learning to model the tail. Advances in Neural Information Processing Systems, 30, 2017.
  37. Heterogeneous domain generalization via domain mixup. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.  3622–3626. IEEE, 2020b.
  38. Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification. In European Conference on Computer Vision, pp.  247–263. Springer, 2020.
  39. Adversarial domain adaptation with domain mixup. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pp.  6502–6509, 2020.
  40. Improve unsupervised domain adaptation with mixup training. arXiv preprint arXiv:2001.00677, 2020.
  41. On multi-domain long-tailed recognition, generalization and beyond. arXiv preprint arXiv:2203.09513, 2022.
  42. Improving out-of-distribution robustness via selective augmentation. arXiv preprint arXiv:2201.00299, 2022.
  43. Few-shot learning via embedding adaptation with set-to-set functions. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp.  8808–8817, 2020.
  44. Procrustean training for imbalanced deep learning. In Proceedings of the IEEE/CVF international conference on computer vision, pp.  92–102, 2021.
  45. Feature transfer learning for face recognition with under-represented data. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp.  5704–5713, 2019.
  46. Domain randomization and pyramid consistency: Simulation-to-real generalization without accessing target domain data. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp.  2100–2110, 2019.
  47. Towards principled disentanglement for domain generalization. In CVPR, 2022.
  48. mixup: Beyond empirical risk minimization. 2018.
  49. Deep long-tailed learning: A survey. arXiv preprint arXiv:2110.04596, 2021.
  50. Learning fast sample re-weighting without reward data. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp.  725–734, 2021.
  51. Improving calibration for long-tailed recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  16489–16498, 2021.
  52. Do deep networks transfer invariances across classes? 2022.
  53. Bbn: Bilateral-branch network with cumulative learning for long-tailed visual recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp.  9719–9728, 2020a.
  54. Domain generalization with optimal transport and metric learning. arXiv preprint arXiv:2007.10573, 2020b.
  55. Deep domain-adversarial image generation for domain generalisation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pp.  13025–13032, 2020c.
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