mlsanityData to 7 Oct 2026

Weakly Supervised Object Localization and Detection: A Survey

arXiv 2104.07918 ↗First posted 16 Apr 2021cs.CVcited by 84

Not on the map. Why?

Abstract (arXiv)

As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems and has received significant attention in the past decade. As methods have been proposed, a comprehensive survey of these topics is of great importance. In this work, we review (1) classic models, (2) approaches with feature representations from off-the-shelf deep networks, (3) approaches solely based on deep learning, and (4) publicly available datasets and standard evaluation metrics that are widely used in this field. We also discuss the key challenges in this field, development history of this field, advantages/disadvantages of the methods in each category, the relationships between methods in different categories, applications of the weakly supervised object localization and detection methods, and potential future directions to further promote the development of this research field.

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Builds on 104 of its 221 references that are in the map. First posted on arXiv 16 Apr 2021.

Builds on

104 of 221 references.

References · 104

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2015Fast R-CNNcited by 2,930
  8. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  9. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  10. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  11. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  12. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
38 more
  1. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  2. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  3. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
  4. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  5. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
  6. 2018Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptationcited by 218
  7. 2017Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localizationcited by 207
  8. 2015Weakly Supervised Deep Detection Networkscited by 183
  9. 2018Adversarial Complementary Learning for Weakly Supervised Object Localizationcited by 166
  10. 2014Simultaneous Detection and Segmentationcited by 158
  11. 2017UntrimmedNets for Weakly Supervised Action Recognition and Detectioncited by 129
  12. 2019Attention-based Dropout Layer for Weakly Supervised Object Localizationcited by 125
  13. 2021TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationcited by 122
  14. 2017CondenseNet: An Efficient DenseNet using Learned Group Convolutionscited by 121
  15. 2016Revisiting Multiple Instance Neural Networkscited by 119
  16. 2017Multiple Instance Detection Network with Online Instance Classifier Refinementcited by 117
  17. 2020Evaluating Weakly Supervised Object Localization Methods Rightcited by 104
  18. 2017Weakly Supervised Action Localization by Sparse Temporal Pooling Networkcited by 100
  19. 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
  20. 2015Webly Supervised Learning of Convolutional Networkscited by 95
  21. 2015Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networkscited by 94
  22. 2020Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detectioncited by 80
  23. 2018AutoLoc: Weakly-supervised Temporal Action Localizationcited by 75
  24. 2018Self-produced Guidance for Weakly-supervised Object Localizationcited by 72
  25. 2019C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detectioncited by 71
  26. 2020SF-Net: Single-Frame Supervision for Temporal Action Localizationcited by 62
  27. 2020Inter-Image Communication for Weakly Supervised Localizationcited by 52
  28. 2020Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detectioncited by 50
  29. 2016Weakly Supervised Cascaded Convolutional Networkscited by 47
  30. 2020Rethinking the Route Towards Weakly Supervised Object Localizationcited by 46
  31. 2019Min-Entropy Latent Model for Weakly Supervised Object Detectioncited by 45
  32. 2015Active Object Localization with Deep Reinforcement Learningcited by 42
  33. 2019Towards Precise End-to-end Weakly Supervised Object Detection Networkcited by 41
  34. 2015Weakly Supervised Object Localization with Multi-fold Multiple Instance Learningcited by 39
  35. 2016ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localizationcited by 39
  36. 2020Geometry Constrained Weakly Supervised Object Localizationcited by 36
  37. 2018Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learningcited by 33
  38. 2018Weakly Supervised Salient Object Detection Using Image Labelscited by 32

50 most cited of 104 All 104 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 20; 2023: 29; 2024: 12; 2025: 13; 2026: 2.

84 papers.

Sort:

By area:

  1. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
  2. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
  3. 2023A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Futurecited by 59
  4. 2022Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imagingcited by 39
  5. 2022Point-to-Box Network for Accurate Object Detection via Single Point Supervisioncited by 31
  6. 2021Few-Shot Object Detection: A Comprehensive Surveycited by 28
  7. 2022Causal Reasoning Meets Visual Representation Learning: A Prospective Studycited by 24
  8. 2023Guided Depth Map Super-resolution: A Surveycited by 23
  9. 2021Background Activation Suppression for Weakly Supervised Object Localizationcited by 22
  10. 2022FedMix: Mixed Supervised Federated Learning for Medical Image Segmentationcited by 22
  11. 2021Background-Click Supervision for Temporal Action Localizationcited by 21
  12. 2022Colar: Effective and Efficient Online Action Detection by Consulting Exemplarscited by 21
38 more
  1. 2022Hybrid Routing Transformer for Zero-Shot Learningcited by 20
  2. 2022Pointly-Supervised Panoptic Segmentationcited by 20
  3. 2021Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teachingcited by 18
  4. 2023TFDet: Target-Aware Fusion for RGB-T Pedestrian Detectioncited by 18
  5. 2023Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentationcited by 17
  6. 2023Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotationscited by 16
  7. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  8. 2022Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videoscited by 12
  9. 2022On Label Granularity and Object Localizationcited by 12
  10. 2023Knowledge Combination to Learn Rotated Detection Without Rotated Annotationcited by 12
  11. 2022Re-Attention Transformer for Weakly Supervised Object Localizationcited by 11
  12. 2023Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Promptcited by 11
  13. 2021A Comparative Review of Recent Few-Shot Object Detection Algorithmscited by 10
  14. 2024Rethinking Early-Fusion Strategies for Improved Multispectral Object Detectioncited by 9
  15. 2025PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detectioncited by 9
  16. 2022Weakly-Supervised Deep Learning Model for Prostate Cancer Diagnosis and Gleason Grading of Histopathology Imagescited by 8
  17. 2024BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labelscited by 8
  18. 2024Pedestrian Attribute Recognition as Label-balanced Multi-label Learningcited by 8
  19. 2025A Multimodal Deviation Perceiving Framework for Weakly-Supervised Temporal Forgery Localizationcited by 8
  20. 2022Structured Attention Composition for Temporal Action Localizationcited by 7
  21. 2023Oriented object detection in optical remote sensing images using deep learning: a surveycited by 7
  22. 2023Image Labels Are All You Need for Coarse Seagrass Segmentationcited by 7
  23. 2023Spatial-Aware Token for Weakly Supervised Object Localizationcited by 7
  24. 2021Learning to ignore: rethinking attention in CNNscited by 6
  25. 2021Background-aware Classification Activation Map for Weakly Supervised Object Localizationcited by 6
  26. 2022Optical Remote Sensing Image Understanding with Weak Supervision: Concepts, Methods, and Perspectivescited by 6
  27. 2026Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoringcited by 6
  28. 2022Compound Batch Normalization for Long-tailed Image Classificationcited by 5
  29. 2023Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metricscited by 5
  30. 2023Weakly Supervised Lesion Detection and Diagnosis for Breast Cancers with Partially Annotated Ultrasound Imagescited by 5
  31. 2023Exploring Effective Priors and Efficient Models for Weakly-Supervised Change Detectioncited by 5
  32. 2022Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstructioncited by 4
  33. 2023Multitask Weakly Supervised Learning for Origin Destination Travel Time Estimationcited by 4
  34. 2023Embrace Limited and Imperfect Training Datasets: Opportunities and Challenges in Plant Disease Recognition Using Deep Learningcited by 4
  35. 2023Weakly supervised information extraction from inscrutable handwritten document imagescited by 4
  36. 2023Co-Learning Meets Stitch-Up for Noisy Multi-label Visual Recognitioncited by 4
  37. 2023Cyclic-Bootstrap Labeling for Weakly Supervised Object Detectioncited by 4
  38. 2024Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentationcited by 4

50 most cited of 84 All 84 (JSON)