End-to-End Semi-Supervised Object Detection with Soft Teacher

• URL: http://arxiv.org/abs/2106.09018v2
• Date: Thu, 17 Jun 2021 16:59:32 GMT
• Title: End-to-End Semi-Supervised Object Detection with Soft Teacher
• Authors: Mengde Xu, Zheng Zhang, Han Hu, Jianfeng Wang, Lijuan Wang, Fangyun Wei, Xiang Bai, Zicheng Liu
• Abstract summary: This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods. The proposed approach outperforms previous methods by a large margin under various labeling ratios. On the state-of-the-art Swin Transformer-based object detector, it can still significantly improve the detection accuracy by +1.5 mAP.
• Score: 63.26266730447914
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods. The end-to-end training gradually improves pseudo label qualities during the curriculum, and the more and more accurate pseudo labels in turn benefit object detection training. We also propose two simple yet effective techniques within this framework: a soft teacher mechanism where the classification loss of each unlabeled bounding box is weighed by the classification score produced by the teacher network; a box jittering approach to select reliable pseudo boxes for the learning of box regression. On COCO benchmark, the proposed approach outperforms previous methods by a large margin under various labeling ratios, i.e. 1\%, 5\% and 10\%. Moreover, our approach proves to perform also well when the amount of labeled data is relatively large. For example, it can improve a 40.9 mAP baseline detector trained using the full COCO training set by +3.6 mAP, reaching 44.5 mAP, by leveraging the 123K unlabeled images of COCO. On the state-of-the-art Swin Transformer-based object detector (58.9 mAP on test-dev), it can still significantly improve the detection accuracy by +1.5 mAP, reaching 60.4 mAP, and improve the instance segmentation accuracy by +1.2 mAP, reaching 52.4 mAP, pushing the new state-of-the-art.

Related papers

• Box-Level Active Detection [47.41635810670186]
  We introduce a box-level active detection framework that controls a box-based budget per cycle. We propose Complementary Pseudo Active Strategy (ComPAS) to exploit both human annotations and the model intelligence. ComPAS consistently outperforms 10 competitors under 4 settings in a unified setting.
  arXiv  Detail & Related papers  (2023-03-23T08:06:10Z)
• Pseudo-label Correction and Learning For Semi-Supervised Object Detection [34.030270359567204]
  We propose two strategies, namely pseudo-label correction and noise-unaware learning. For pseudo-label correction, we introduce a multi-round refining method and a multi-vote weighting method. For noise-unaware learning, we introduce a loss weight function that is negatively correlated with the Intersection over Union (IoU) in the regression task.
  arXiv  Detail & Related papers  (2023-03-06T09:54:15Z)
• Label, Verify, Correct: A Simple Few Shot Object Detection Method [93.84801062680786]
  We introduce a simple pseudo-labelling method to source high-quality pseudo-annotations from a training set. We present two novel methods to improve the precision of the pseudo-labelling process. Our method achieves state-of-the-art or second-best performance compared to existing approaches.
  arXiv  Detail & Related papers  (2021-12-10T18:59:06Z)
• Robust and Accurate Object Detection via Self-Knowledge Distillation [9.508466066051572]
  Unified Decoupled Feature Alignment (UDFA) is a novel fine-tuning paradigm which achieves better performance than existing methods. We show that UDFA can surpass the standard training and state-of-the-art adversarial training methods for object detection.
  arXiv  Detail & Related papers  (2021-11-14T04:40:15Z)
• Towards Reducing Labeling Cost in Deep Object Detection [61.010693873330446]
  We propose a unified framework for active learning, that considers both the uncertainty and the robustness of the detector. Our method is able to pseudo-label the very confident predictions, suppressing a potential distribution drift.
  arXiv  Detail & Related papers  (2021-06-22T16:53:09Z)
• Rethinking Pseudo Labels for Semi-Supervised Object Detection [84.697097472401]
  We introduce certainty-aware pseudo labels tailored for object detection. We dynamically adjust the thresholds used to generate pseudo labels and reweight loss functions for each category to alleviate the class imbalance problem. Our approach improves supervised baselines by up to 10% AP using only 1-10% labeled data from COCO.
  arXiv  Detail & Related papers  (2021-06-01T01:32:03Z)
• Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework [14.914115746675176]
  Semi-supervised object detection can leverage unlabeled data to improve the model performance. We propose Instant-Teaching, which uses instant pseudo labeling with extended weak-strong data augmentations for teaching during each training iteration. Our method surpasses state-of-the-art methods by 4.2 mAP on MS-COCO when using $2%$ labeled data.
  arXiv  Detail & Related papers  (2021-03-21T14:03:36Z)
• Unbiased Teacher for Semi-Supervised Object Detection [50.0087227400306]
  We revisit the Semi-Supervised Object Detection (SS-OD) and identify the pseudo-labeling bias issue in SS-OD. We introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner.
  arXiv  Detail & Related papers  (2021-02-18T17:02:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.