mlsanityData to 7 Oct 2026

Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization

arXiv 1704.04232 ↗First posted 13 Apr 2017cs.CVcited by 207

Not on the map. Why?

Abstract (arXiv)

We propose `Hide-and-Seek', a weakly-supervised framework that aims to improve object localization in images and action localization in videos. Most existing weakly-supervised methods localize only the most discriminative parts of an object rather than all relevant parts, which leads to suboptimal performance. Our key idea is to hide patches in a training image randomly, forcing the network to seek other relevant parts when the most discriminative part is hidden. Our approach only needs to modify the input image and can work with any network designed for object localization. During testing, we do not need to hide any patches. Our Hide-and-Seek approach obtains superior performance compared to previous methods for weakly-supervised object localization on the ILSVRC dataset. We also demonstrate that our framework can be easily extended to weakly-supervised action localization.

Key facts. Cited by 207 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 64; 2022: 54; 2023: 35; 2024: 29; 2025: 17; 2026: 8.

207 papers.

Sort:

By area:

  1. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  2. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
  3. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  4. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  5. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  6. 2021TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationcited by 122
  7. 2021UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modelingcited by 122
  8. 2021Large-scale Unsupervised Semantic Segmentationcited by 98
  9. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
  10. 2022Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigationcited by 86
  11. 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
  12. 2022Learning Affordance Grounding from Exocentric Imagescited by 82
38 more
  1. 2021Complementary Patch for Weakly Supervised Semantic Segmentationcited by 75
  2. 2022A Closer Look at Weakly-Supervised Audio-Visual Source Localizationcited by 72
  3. 2021CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learningcited by 69
  4. 2021Improving Deep Learning Interpretability by Saliency Guided Trainingcited by 68
  5. 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
  6. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  7. 2023Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentationcited by 53
  8. 2022Correlation Verification for Image Retrievalcited by 47
  9. 2021Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localizationcited by 46
  10. 2021A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localizationcited by 45
  11. 2021Learning Action Completeness from Points for Weakly-supervised Temporal Action Localizationcited by 42
  12. 2022Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationcited by 41
  13. 2022ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localizationcited by 39
  14. 2024A Comprehensive Survey on Data Augmentationcited by 38
  15. 2021Weakly Supervised Temporal Adjacent Network for Language Groundingcited by 37
  16. 2022Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentationcited by 37
  17. 2021Shallow Feature Matters for Weakly Supervised Object Localizationcited by 34
  18. 2021SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detectioncited by 34
  19. 2022Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localizationcited by 33
  20. 2021Deep Learning-based Action Detection in Untrimmed Videos: A Surveycited by 32
  21. 2021Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localizationcited by 30
  22. 2023CUDA: Curriculum of Data Augmentation for Long-Tailed Recognitioncited by 30
  23. 2021Self-supervised object detection from audio-visual correspondencecited by 29
  24. 2021Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentationcited by 29
  25. 2021Action Unit Memory Network for Weakly Supervised Temporal Action Localizationcited by 26
  26. 2021Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localizationcited by 26
  27. 2021F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscalingcited by 26
  28. 2022Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentationcited by 26
  29. 2021Survey: Image Mixing and Deleting for Data Augmentationcited by 25
  30. 2022Bridging the Gap between Classification and Localization for Weakly Supervised Object Localizationcited by 25
  31. 2021LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localizationcited by 24
  32. 2021Learning Representational Invariances for Data-Efficient Action Recognitioncited by 22
  33. 2021Background Activation Suppression for Weakly Supervised Object Localizationcited by 22
  34. 2023MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentationcited by 22
  35. 2021Weakly Supervised Action Selection Learning in Videocited by 21
  36. 2021Improving Pneumonia Localization via Cross-Attention on Medical Images and Reportscited by 21
  37. 2022Model-Agnostic Augmentation for Accurate Graph Classificationcited by 21
  38. 2022CREAM: Weakly Supervised Object Localization via Class RE-Activation Mappingcited by 21

50 most cited of 207 All 207 (JSON)