Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

Low-Confidence Samples Mining for Semi-supervised Object Detection (2306.16201v1)

Published 28 Jun 2023 in cs.CV

Abstract: Reliable pseudo-labels from unlabeled data play a key role in semi-supervised object detection (SSOD). However, the state-of-the-art SSOD methods all rely on pseudo-labels with high confidence, which ignore valuable pseudo-labels with lower confidence. Additionally, the insufficient excavation for unlabeled data results in an excessively low recall rate thus hurting the network training. In this paper, we propose a novel Low-confidence Samples Mining (LSM) method to utilize low-confidence pseudo-labels efficiently. Specifically, we develop an additional pseudo information mining (PIM) branch on account of low-resolution feature maps to extract reliable large-area instances, the IoUs of which are higher than small-area ones. Owing to the complementary predictions between PIM and the main branch, we further design self-distillation (SD) to compensate for both in a mutually-learning manner. Meanwhile, the extensibility of the above approaches enables our LSM to apply to Faster-RCNN and Deformable-DETR respectively. On the MS-COCO benchmark, our method achieves 3.54% mAP improvement over state-of-the-art methods under 5% labeling ratios.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Mixmatch: a holistic approach to semi-supervised learning. In NeurIPS, volume 32, 2019.
  2. End-to-end object detection with transformers. In ECCV, pages 213–229, 2020.
  3. Label matching semi-supervised object detection. In CVPR, pages 14381–14390, 2022.
  4. Dense learning based semi-supervised object detection. In CVPR, pages 4815–4824, 2022.
  5. Boundary-preserving mask r-cnn. In ECCV, pages 660–676, 2020.
  6. {ImageNet}: a large-scale hierarchical image database. In CVPR, pages 248–255, 2009.
  7. The pascal visual object classes (voc) challenge. pages 303–338, 2010.
  8. Scale-equivalent distillation for semi-supervised object detection. In CVPR, pages 14522–14531, 2022.
  9. Mask r-cnn. In ICCV, pages 2961–2969, 2017.
  10. Averaging weights leads to wider optima and better generalization. In arXiv preprint arXiv:1803.05407, 2018.
  11. Consistency-based semi-supervised learning for object detection. In NeurIPS, volume 32, 2019.
  12. Probabilistic anchor assignment with iou prediction for object detection. In ECCV, pages 355–371, 2020.
  13. Mum: mix image tiles and unmix feature tiles for semi-supervised object detection. In CVPR, pages 14512–14521, 2022.
  14. Scale-aware trident networks for object detection. In ICCV, pages 6054–6063, 2019.
  15. Pseco: pseudo labeling and consistency training for semi-supervised object detection. In ECCV, pages 1–17, 2022.
  16. Rethinking pseudo labels for semi-supervised object detection. In AAAI, pages 1314–1322, 2022.
  17. Microsoft {COCO}: common objects in context. In ECCV, pages 740–755, 2014.
  18. A survey of deep neural network architectures and their applications. In Neurocomputing, pages 11–26, 2017.
  19. Unbiased teacher for semi-supervised object detection. In ICLR, pages 1–17, 2021.
  20. Faster r-cnn: towards real-time object detection with region proposal networks. In NeurIPS, volume 28, 2015.
  21. Regularization with stochastic transformations and perturbations for deep semi-supervised learning. In NeurIPS, volume 29, 2016.
  22. Objects365: a large-scale, high-quality dataset for object detection. In ICCV, pages 8430–8439, 2019.
  23. Sniper: efficient multi-scale training. In NeurIPS, volume 31, 2018.
  24. Fixmatch: simplifying semi-supervised learning with consistency and confidence. In NeurIPS, pages 596–608, 2020.
  25. A simple semi-supervised learning framework for object detection. In arXiv preprint arXiv:2005.04757, 2020.
  26. Humble teachers teach better students for semi-supervised object detection. In CVPR, pages 3132–3141, 2021.
  27. Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In NeurIPS, volume 30, 2017.
  28. Double-check soft teacher for semi-supervised object detection. In IJCAI, pages 1430–1436, 2022.
  29. Unsupervised data augmentation for consistency training. In NeurIPS, pages 6256–6268, 2020.
  30. Self-training with noisy student improves imagenet classification. In CVPR, pages 10687–10698, 2020.
  31. End-to-end semi-supervised object detection with soft teacher. In ICCV, pages 3060–3069, 2021.
  32. Interactive self-training with mean teachers for semi-supervised object detection. In CVPR, pages 5941–5950, 2021.
  33. Semi-supervised object detection with adaptive class-rebalancing self-training. In AAAI, pages 3252–3261, 2022.
  34. Dual decoupling training for semi-supervised object detection with noise-bypass head. In AAAI, pages 3526–3534, 2022.
  35. Instant-teaching: an end-to-end semi-supervised object detection framework. In CVPR, pages 4081–4090, 2021.
  36. Deformable detr: deformable transformers for end-to-end object detection. In ICLR, pages 1–16, 2021.
Citations (1)
View on Semantic Scholar

Summary

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

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