mlsanityData to 7 Oct 2026

Online progressive instance-balanced sampling for weakly supervised object detection

arXiv 2206.10324 ↗First posted 21 Jun 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Based on multiple instance detection networks (MIDN), plenty of works have contributed tremendous efforts to weakly supervised object detection (WSOD). However, most methods neglect the fact that the overwhelming negative instances exist in each image during the training phase, which would mislead the training and make the network fall into local minima. To tackle this problem, an online progressive instance-balanced sampling (OPIS) algorithm based on hard sampling and soft sampling is proposed in this paper. The algorithm includes two modules: a progressive instance balance (PIB) module and a progressive instance reweighting (PIR) module. The PIB module combining random sampling and IoU-balanced sampling progressively mines hard negative instances while balancing positive instances and negative instances. The PIR module further utilizes classifier scores and IoUs of adjacent refinements to reweight the weights of positive instances for making the network focus on positive instances. Extensive experimental results on the PASCAL VOC 2007 and 2012 datasets demonstrate the proposed method can significantly improve the baseline, which is also comparable to many existing state-of-the-art results. In addition, compared to the baseline, the proposed method requires no extra network parameters and the supplementary training overheads are small, which could be easily integrated into other methods based on the instance classifier refinement paradigm.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 62 references that are in the map. First posted on arXiv 21 Jun 2022.

Builds on

35 of 62 references.

References · 35

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2017Mask R-CNNcited by 7,259
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  4. 2015Fast R-CNNcited by 2,930
  5. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  6. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  7. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  8. 2015Weakly Supervised Deep Detection Networkscited by 183
  9. 2017Multiple Instance Detection Network with Online Instance Classifier Refinementcited by 117
  10. 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
  11. 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
  12. 2020Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detectioncited by 80
23 more
  1. 2019C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detectioncited by 71
  2. 2019Prime Sample Attention in Object Detectioncited by 55
  3. 2019WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detectioncited by 51
  4. 2020Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detectioncited by 50
  5. 2016Weakly Supervised Cascaded Convolutional Networkscited by 47
  6. 2019Min-Entropy Latent Model for Weakly Supervised Object Detectioncited by 45
  7. 2019Towards Precise End-to-end Weakly Supervised Object Detection Networkcited by 41
  8. 2015Weakly Supervised Object Localization with Multi-fold Multiple Instance Learningcited by 39
  9. 2016ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localizationcited by 39
  10. 2018Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learningcited by 33
  11. 2020SLV: Spatial Likelihood Voting for Weakly Supervised Object Detectioncited by 29
  12. 2019Weakly Supervised Object Detection with Segmentation Collaborationcited by 26
  13. 2018Zigzag Learning for Weakly Supervised Object Detectioncited by 24
  14. 2018Dissimilarity Coefficient based Weakly Supervised Object Detectioncited by 23
  15. 2018TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detectioncited by 22
  16. 2017C-WSL: Count-guided Weakly Supervised Localizationcited by 20
  17. 2021Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusterscited by 20
  18. 2020Object Instance Mining for Weakly Supervised Object Detectioncited by 18
  19. 2017Multiple Instance Curriculum Learning for Weakly Supervised Object Detectioncited by 13
  20. 2019Object-Aware Instance Labeling for Weakly Supervised Object Detectioncited by 11
  21. 2019Utilizing the Instability in Weakly Supervised Object Detectioncited by 7
  22. 2020Distilling Knowledge from Refinement in Multiple Instance Detection Networkscited by 1
  23. 2021Online Active Proposal Set Generation for Weakly Supervised Object Detectioncited by 1

Built on by

Not cited yet.