mlsanityData to 7 Oct 2026

Salvage of Supervision in Weakly Supervised Object Detection

arXiv 2106.04073 ↗First posted 8 Jun 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Weakly supervised object detection~(WSOD) has recently attracted much attention. However, the lack of bounding-box supervision makes its accuracy much lower than fully supervised object detection (FSOD), and currently modern FSOD techniques cannot be applied to WSOD. To bridge the performance and technical gaps between WSOD and FSOD, this paper proposes a new framework, Salvage of Supervision (SoS), with the key idea being to harness every potentially useful supervisory signal in WSOD: the weak image-level labels, the pseudo-labels, and the power of semi-supervised object detection. This paper proposes new approaches to utilize these weak and noisy signals effectively, and shows that each type of supervisory signal brings in notable improvements, outperforms existing WSOD methods (which mainly use only the weak labels) by large margins. The proposed SoS-WSOD method also has the ability to freely use modern FSOD techniques. SoS-WSOD achieves 64.4 mAP50 on VOC2007, 61.9 mAP50 on VOC2012 and 16.6 mAP50:95 on MS-COCO, and also has fast inference speed. Ablations and visualization further verify the effectiveness of SoS.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 8 Jun 2021.

Builds on

31 of 44 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017Mask R-CNNcited by 7,259
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2015Fast R-CNNcited by 2,930
  8. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  9. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  10. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  11. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  12. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
19 more
  1. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  2. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  3. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  4. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  5. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  6. 2015Weakly Supervised Deep Detection Networkscited by 183
  7. 2017Multiple Instance Detection Network with Online Instance Classifier Refinementcited by 117
  8. 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
  9. 2020Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detectioncited by 80
  10. 2019C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detectioncited by 71
  11. 2019WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detectioncited by 51
  12. 2020Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detectioncited by 50
  13. 2019Towards Precise End-to-end Weakly Supervised Object Detection Networkcited by 41
  14. 2019Learning from Noisy Anchors for One-stage Object Detectioncited by 35
  15. 2018Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detectioncited by 32
  16. 2020SLV: Spatial Likelihood Voting for Weakly Supervised Object Detectioncited by 29
  17. 2020Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfercited by 28
  18. 2018Dissimilarity Coefficient based Weakly Supervised Object Detectioncited by 23
  19. 2020Object Instance Mining for Weakly Supervised Object Detectioncited by 18

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 4.

8 papers.

  1. 2022BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentationcited by 31
  2. 2024WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognitioncited by 9
  3. 2024Complete Instances Mining for Weakly Supervised Instance Segmentationcited by 5
  4. 2023Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depthcited by 4
  5. 2023Cyclic-Bootstrap Labeling for Weakly Supervised Object Detectioncited by 4
  6. 2023Transformer-based Multi-Instance Learning for Weakly Supervised Object Detectioncited by 0
  7. 2024Negative Prototypes Guided Contrastive Learning for WSODcited by 0
  8. 2024Enhancing Weakly-Supervised Object Detection on Static Images through (Hallucinated) Motioncited by 0