mlsanityData to 7 Oct 2026

Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization

arXiv 2204.00220 ↗First posted 1 Apr 2022cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels. Most existing methods use a class activation map (CAM) to generate a localization map; however, a CAM identifies only the most discriminative parts of a target object rather than the entire object region. In this work, we find the gap between classification and localization in terms of the misalignment of the directions between an input feature and a class-specific weight. We demonstrate that the misalignment suppresses the activation of CAM in areas that are less discriminative but belong to the target object. To bridge the gap, we propose a method to align feature directions with a class-specific weight. The proposed method achieves a state-of-the-art localization performance on the CUB-200-2011 and ImageNet-1K benchmarks.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 1 Apr 2022.

Builds on

25 of 36 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  8. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  9. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  10. 2013Network In Networkcited by 600
  11. 2017Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localizationcited by 207
  12. 2018Adversarial Complementary Learning for Weakly Supervised Object Localizationcited by 166
13 more
  1. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  2. 2019Attention-based Dropout Layer for Weakly Supervised Object Localizationcited by 125
  3. 2019Large-scale interactive object segmentation with human annotatorscited by 109
  4. 2018Self-produced Guidance for Weakly-supervised Object Localizationcited by 72
  5. 2020Inter-Image Communication for Weakly Supervised Localizationcited by 52
  6. 2020Rethinking the Route Towards Weakly Supervised Object Localizationcited by 46
  7. 2021Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localizationcited by 46
  8. 2021Shallow Feature Matters for Weakly Supervised Object Localizationcited by 34
  9. 2021Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localizationcited by 30
  10. 2020Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasetscited by 19
  11. 2021Normalization Matters in Weakly Supervised Object Localizationcited by 19
  12. 2020In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object Localizationcited by 16
  13. 2021Keep CALM and Improve Visual Feature Attributioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 12; 2024: 5; 2025: 2; 2026: 1.

25 papers.

Sort:

  1. 2023Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervisioncited by 99
  2. 2023LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Groundingcited by 64
  3. 2022Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibrationcited by 20
  4. 2023Generative Prompt Model for Weakly Supervised Object Localizationcited by 20
  5. 2023Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentationcited by 17
  6. 2022Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localizationcited by 13
  7. 2022Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localizationcited by 12
  8. 2023DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localizationcited by 8
  9. 2023Spatial-Aware Token for Weakly Supervised Object Localizationcited by 7
  10. 2024A Weakly Supervised and Globally Explainable Learning Framework for Brain Tumor Segmentationcited by 6
  11. 2023Knowledge-guided Causal Intervention for Weakly-supervised Object Localizationcited by 4
  12. 2023Top-Down Framework for Weakly-supervised Grounded Image Captioningcited by 4
13 more
  1. 2025Closed-Loop Transfer for Weakly-supervised Affordance Groundingcited by 4
  2. 2023Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localizationcited by 3
  3. 2023Unsupervised Object Localization with Representer Point Selectioncited by 3
  4. 2023Open-World Weakly-Supervised Object Localizationcited by 2
  5. 2023Boosting Weakly-Supervised Image Segmentation via Representation, Transform, and Compensatorcited by 2
  6. 2024CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspectivecited by 2
  7. 2024Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentationcited by 2
  8. 2022ExpNet: A unified network for Expert-Level Classificationcited by 1
  9. 2022Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructurescited by 0
  10. 2024Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognitioncited by 0
  11. 2024Graphical Perception of Saliency-based Model Explanationscited by 0
  12. 2025RASALoRE: Region Aware Spatial Attention with Location-based Random Embeddings for Weakly Supervised Anomaly Detection in Brain MRI Scanscited by 0
  13. 2026TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglementcited by 0