mlsanityData to 7 Oct 2026

Rethinking the Route Towards Weakly Supervised Object Localization

arXiv 2002.11359 ↗First posted 26 Feb 2020cs.CVcited by 46

Not on the map. Why?

Abstract (arXiv)

Weakly supervised object localization (WSOL) aims to localize objects with only image-level labels. Previous methods often try to utilize feature maps and classification weights to localize objects using image level annotations indirectly. In this paper, we demonstrate that weakly supervised object localization should be divided into two parts: class-agnostic object localization and object classification. For class-agnostic object localization, we should use class-agnostic methods to generate noisy pseudo annotations and then perform bounding box regression on them without class labels. We propose the pseudo supervised object localization (PSOL) method as a new way to solve WSOL. Our PSOL models have good transferability across different datasets without fine-tuning. With generated pseudo bounding boxes, we achieve 58.00% localization accuracy on ImageNet and 74.97% localization accuracy on CUB-200, which have a large edge over previous models.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 14; 2023: 12; 2024: 5; 2025: 3; 2026: 3.

46 papers.

Sort:

  1. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
  2. 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
  3. 2021Shallow Feature Matters for Weakly Supervised Object Localizationcited by 34
  4. 2021Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localizationcited by 30
  5. 2021F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscalingcited by 26
  6. 2022Bridging the Gap between Classification and Localization for Weakly Supervised Object Localizationcited by 25
  7. 2021LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localizationcited by 24
  8. 2021Background Activation Suppression for Weakly Supervised Object Localizationcited by 22
  9. 2022CREAM: Weakly Supervised Object Localization via Class RE-Activation Mappingcited by 21
  10. 2022Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibrationcited by 20
  11. 2023Generative Prompt Model for Weakly Supervised Object Localizationcited by 20
  12. 2022HINT: Hierarchical Neuron Concept Explainercited by 17
34 more
  1. 2023Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentationcited by 17
  2. 2022Weakly Supervised Object Localization as Domain Adaptioncited by 16
  3. 2021A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applicationscited by 14
  4. 2022Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localizationcited by 13
  5. 2022TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videoscited by 12
  6. 2022What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputscited by 11
  7. 2022Bagging Regional Classification Activation Maps for Weakly Supervised Object Localizationcited by 9
  8. 2024Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histologycited by 9
  9. 2022Negative Evidence Matters in Interpretable Histology Image Classificationcited by 8
  10. 2023DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localizationcited by 8
  11. 2022Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentationcited by 7
  12. 2023CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videoscited by 7
  13. 2023Spatial-Aware Token for Weakly Supervised Object Localizationcited by 7
  14. 2021Background-aware Classification Activation Map for Weakly Supervised Object Localizationcited by 6
  15. 2022CaFT: Clustering and Filter on Tokens of Transformer for Weakly Supervised Object Localizationcited by 4
  16. 2023Knowledge-guided Causal Intervention for Weakly-supervised Object Localizationcited by 4
  17. 2023Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localizationcited by 3
  18. 2023Unsupervised Object Localization with Representer Point Selectioncited by 3
  19. 2023FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localizationcited by 3
  20. 2024Towards Two-Stream Foveation-based Active Vision Learningcited by 3
  21. 2023Rethinking the Localization in Weakly Supervised Object Localizationcited by 2
  22. 2023Semantic-Constraint Matching Transformer for Weakly Supervised Object Localizationcited by 2
  23. 2024Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Labelcited by 2
  24. 2024Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videoscited by 2
  25. 2025TeD-Loc: Text Distillation for Weakly Supervised Object Localizationcited by 2
  26. 2025PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localizationcited by 2
  27. 2026Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardwarecited by 2
  28. 2021Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detectioncited by 1
  29. 2025Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localizationcited by 1
  30. 2022Learning Consistency from High-quality Pseudo-labels for Weakly Supervised Object Localizationcited by 0
  31. 2023Multiscale Vision Transformer With Deep Clustering-Guided Refinement for Weakly Supervised Object Localizationcited by 0
  32. 2024Categorical Knowledge Fused Recognition: Fusing Hierarchical Knowledge with Image Classification through Aligning and Deep Metric Learningcited by 0
  33. 2026From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual Understandingcited by 0
  34. 2026EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAIcited by 0