Papers
Topics
Authors
Recent
Search
2000 character limit reached

Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond

Published 18 Mar 2023 in cs.CV, cs.AI, and cs.LG | (2303.10343v2)

Abstract: The success of data mixing augmentations in image classification tasks has been well-received. However, these techniques cannot be readily applied to object detection due to challenges such as spatial misalignment, foreground/background distinction, and plurality of instances. To tackle these issues, we first introduce a novel conceptual framework called Supervision Interpolation (SI), which offers a fresh perspective on interpolation-based augmentations by relaxing and generalizing Mixup. Based on SI, we propose LossMix, a simple yet versatile and effective regularization that enhances the performance and robustness of object detectors and more. Our key insight is that we can effectively regularize the training on mixed data by interpolating their loss errors instead of ground truth labels. Empirical results on the PASCAL VOC and MS COCO datasets demonstrate that LossMix can consistently outperform state-of-the-art methods widely adopted for detection. Furthermore, by jointly leveraging LossMix with unsupervised domain adaptation, we successfully improve existing approaches and set a new state of the art for cross-domain object detection.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (76)
  1. Keep it Simple: Image Statistics Matching for Domain Adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops.
  2. AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation. In Proceedings of the International Conference on Learning Representations (ICLR).
  3. Single-Channel Speech Enhancement Using Learnable Loss Mixup. In Proc. Interspeech 2021, 2696–2700.
  4. Harmonizing transferability and discriminability for adapting object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  5. SuperMix: Supervising the Mixing Data Augmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  6. Deng; Jia; Dong; Wei; Socher; Richard; Li; Li-Jia; Li; Kai; Fei-Fei; and Li. 2009. Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  7. Unbiased Mean Teacher for Cross-domain Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  8. The Pascal Visual Object Classes (VOC) challenge. International Journal of Computer Vision, 88: 303–338.
  9. Domain-Adversarial Training of Neural Networks. In JMLR.
  10. AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection. In Proceedings of the European Conference on Computer Vision (ECCV).
  11. YOLOX: Exceeding YOLO Series in 2021. arXiv:2107.08430.
  12. PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV).
  13. Unsupervised Domain Generalization by Learning a Bridge Across Domains. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  14. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  15. Cycada: Cycle-consistent adversarial domain adaptation. In Proceedings of the International Conference on Machine Learning (ICML).
  16. StyleMix: Separating Content and Style for Enhanced Data Augmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  17. DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  18. Progressive domain adaptation for object detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
  19. Cross-domain weakly-supervised object detection through progressive domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  20. Interpolation-based semi-supervised learning for object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  21. Jocher, G. 2020. YOLOv5 by Ultralytics.
  22. YOLO by Ultralytics.
  23. Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup. In Proceedings of the International Conference on Machine Learning (ICML).
  24. Diversify and match: A domain adaptive representation learning paradigm for object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  25. Dranet: Disentangling representation and adaptation networks for unsupervised cross-domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  26. OpenMixup: A Comprehensive Mixup Benchmark for Visual Classification. arXiv:2209.04851.
  27. Deep Domain Adaptive Object Detection: a Survey. In SSCI.
  28. Cross-Domain Adaptive Teacher for Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  29. DINE: Domain Adaptation from Single and Multiple Black-box Predictors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  30. Feature pyramid networks for object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  31. Microsoft coco: Common objects in context. In Proceedings of the European Conference on Computer Vision (ECCV).
  32. TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers. In Proceedings of the European Conference on Computer Vision (ECCV).
  33. SSD: Single Shot MultiBox Detector. In Proceedings of the European Conference on Computer Vision (ECCV).
  34. Leveraging Self-Supervision for Cross-Domain Crowd Counting. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  35. Geometric and Textural Augmentation for Domain Gap Reduction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  36. AutoMix: Unveiling the Power of Mixup for Stronger Classifiers. In Proceedings of the European Conference on Computer Vision (ECCV).
  37. Over-training with Mixup May Hurt Generalization. In Proceedings of the International Conference on Learning Representations (ICLR).
  38. Learning transferable features with deep adaptation networks. In Proceedings of the International Conference on Machine Learning (ICML).
  39. Conditional adversarial domain adaptation. In Advances in Neural Information Processing Systems (NeurIPS).
  40. Unsupervised domain adaptation with residual transfer networks. In Advances in Neural Information Processing Systems (NeurIPS).
  41. Pareto Domain Adaptation. In Advances in Neural Information Processing Systems (NeurIPS).
  42. Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  43. Slimmable Domain Adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  44. SSAL: Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection. In Advances in Neural Information Processing Systems (NeurIPS).
  45. Image to image translation for domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  46. FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  47. Unsupervised Domain Adaptation of Object Detectors: A Survey. arXiv:2105.13502.
  48. RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness. In Advances in Neural Information Processing Systems (NeurIPS).
  49. SimROD: A Simple Adaptation Method for Robust Object Detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV).
  50. A Closer Look at Smoothness in Domain Adversarial Training. In Proceedings of the International Conference on Machine Learning (ICML).
  51. You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  52. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems (NeurIPS).
  53. Strong-weak distribution alignment for adaptive object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  54. SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses. arXiv:1911.02559.
  55. FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence. In Advances in Neural Information Processing Systems (NeurIPS).
  56. Return of Frustratingly Easy Domain Adaptation. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).
  57. Safe Self-Refinement for Transformer-based Domain Adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  58. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In Advances in Neural Information Processing Systems (NeurIPS).
  59. AlignMixup: Improving Representations by Interpolating Aligned Features. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 19174–19183.
  60. Interpolation consistency training for semi-supervised learning. Neural Networks, 145: 90–106.
  61. Manifold Mixup: Better Representations by Interpolating Hidden States. In Chaudhuri, K.; and Salakhutdinov, R., eds., Proceedings of the International Conference on Machine Learning (ICML), volume 97 of Proceedings of Machine Learning Research, 6438–6447. Long Beach, California, USA: PMLR.
  62. AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection. IEEE Transactions on Image Processing, 30: 4046–4056.
  63. Seesaw Loss for Long-Tailed Instance Segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  64. Dual Mixup Regularized Learning for Adversarial Domain Adaptation. In Proceedings of the European Conference on Computer Vision (ECCV).
  65. Detectron2. https://github.com/facebookresearch/detectron2.
  66. Exploring categorical regularization for domain adaptive object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  67. Adversarial Domain Adaptation with Domain Mixup. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).
  68. A Small Object Detection Algorithm Based on Modulated Deformable Convolution and Large Kernel Convolution. Intell. Neuroscience, 2023.
  69. CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV).
  70. Mixup-CIFAR10. https://github.com/facebookresearch/mixup-cifar10/blob/main/train.py“#L138.
  71. Mixup: Beyond empirical risk minimization. In Proceedings of the International Conference on Learning Representations (ICLR).
  72. Lightweight object detection algorithm based on YOLOv5 for unmanned surface vehicles. Frontiers in Marine Science, 9.
  73. ByteTrack: Multi-Object Tracking by Associating Every Detection Box. In Proceedings of the European Conference on Computer Vision (ECCV).
  74. Bag of Freebies for Training Object Detection Neural Networks. arXiv:1902.04103.
  75. Dual Decoupling Training for Semi-supervised Object Detection with Noise-Bypass Head. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).
  76. Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up