mlsanityData to 14 Oct 2026

Learning Deep Features for Discriminative Localization

arXiv 1512.04150 ↗First posted 14 Dec 2015cs.CVcited by 2,436

Not on the map. Why?

Cited by 44 in Knowledge distillation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels. While this technique was previously proposed as a means for regularizing training, we find that it actually builds a generic localizable deep representation that can be applied to a variety of tasks. Despite the apparent simplicity of global average pooling, we are able to achieve 37.1% top-5 error for object localization on ILSVRC 2014, which is remarkably close to the 34.2% top-5 error achieved by a fully supervised CNN approach. We demonstrate that our network is able to localize the discriminative image regions on a variety of tasks despite not being trained for them

Key facts. Cited by 2,436 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Dec 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 588; 2022: 512; 2023: 492; 2024: 389; 2025: 293; 2026: 162.

2,436 papers.

Sort:

By area:

  1. 2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 473
  2. 2021Deep Long-Tailed Learning: A Surveycited by 417
  3. 2021Dynamic Neural Networks: A Surveycited by 408
  4. 2021Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigmcited by 405
  5. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 386
  6. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  7. 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
  8. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 320
  9. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  10. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  11. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  12. 2022Visual Attention Networkcited by 210
38 more
  1. 2021Trustworthy AI: From Principles to Practicescited by 207
  2. 2021Simultaneously Localize, Segment and Rank the Camouflaged Objectscited by 198
  3. 2022Focal Modulation Networkscited by 186
  4. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 178
  5. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 167
  6. 2021Conformer: Local Features Coupling Global Representations for Visual Recognitioncited by 164
  7. 2022Audio-Visual Segmentationcited by 151
  8. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  9. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  10. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  11. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  12. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  13. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  14. 2023Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detectioncited by 127
  15. 2021TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationcited by 123
  16. 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 123
  17. 2021UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modelingcited by 122
  18. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
  19. 2021Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labelscited by 118
  20. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 118
  21. 2022Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformerscited by 118
  22. 2022CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentationcited by 118
  23. 2022ReCo: Retrieve and Co-segment for Zero-shot Transfercited by 117
  24. 2022UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormercited by 116
  25. 2021Salient ImageNet: How to discover spurious features in Deep Learning?cited by 114
  26. 2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
  27. 2021Representative Forgery Mining for Fake Face Detectioncited by 108
  28. 2022Attention Spiking Neural Networkscited by 107
  29. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 105
  30. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  31. 2022PlanT: Explainable Planning Transformers via Object-Level Representationscited by 105
  32. 2021Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillationcited by 104
  33. 2023R2Former: Unified Retrieval and Reranking Transformer for Place Recognitioncited by 102
  34. 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
  35. 2021Large-scale Unsupervised Semantic Segmentationcited by 101
  36. 2023Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervisioncited by 99
  37. 2021Do Feature Attribution Methods Correctly Attribute Features?cited by 98
  38. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 98

50 most cited of 2,436 All 2,436 (JSON)