mlsanityData to 7 Oct 2026

BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation

arXiv 2103.08907 ↗First posted 16 Mar 2021cs.CVcited by 104

Not on the map. Why?

Abstract (arXiv)

Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object. Existing methods typically depend on a class-agnostic mask generator, which operates on the low-level information intrinsic to an image. In this work, we utilize higher-level information from the behavior of a trained object detector, by seeking the smallest areas of the image from which the object detector produces almost the same result as it does from the whole image. These areas constitute a bounding-box attribution map (BBAM), which identifies the target object in its bounding box and thus serves as pseudo ground-truth for weakly supervised semantic and instance segmentation. This approach significantly outperforms recent comparable techniques on both the PASCAL VOC and MS COCO benchmarks in weakly supervised semantic and instance segmentation. In addition, we provide a detailed analysis of our method, offering deeper insight into the behavior of the BBAM.

Key facts. Cited by 104 papers in the map (data through 7 Oct 2026). Builds on 49 of its 70 references that are in the map. First posted on arXiv 16 Mar 2021.

Builds on

49 of 70 references.

References · 49

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Mask R-CNNcited by 7,259
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  10. 2015Fast R-CNNcited by 2,930
  11. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  12. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
37 more
  1. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  2. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  3. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  4. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  5. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  6. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  7. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  8. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 245
  9. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  10. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
  11. 2019Visualizing and Measuring the Geometry of BERTcited by 215
  12. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  13. 2015Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentationcited by 189
  14. 2019FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inferencecited by 162
  15. 2018Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentationcited by 145
  16. 2020Weakly-Supervised Semantic Segmentation via Sub-category Explorationcited by 145
  17. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  18. 2020Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentationcited by 144
  19. 2015Instance-aware Semantic Segmentation via Multi-task Network Cascadescited by 120
  20. 2018Normalized Cut Loss for Weakly-supervised CNN Segmentationcited by 112
  21. 2020Restricting the Flow: Information Bottlenecks for Attributioncited by 110
  22. 2019Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentationcited by 97
  23. 2018Self-Erasing Network for Integral Object Attentioncited by 95
  24. 2015Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generationcited by 90
  25. 2018CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentationcited by 80
  26. 2018Weakly Supervised Instance Segmentation using Class Peak Responsecited by 74
  27. 2019Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentationcited by 58
  28. 2017Weakly Supervised Semantic Segmentation using Web-Crawled Videoscited by 38
  29. 2019Object Counting and Instance Segmentation with Image-level Supervisioncited by 35
  30. 2019Grid Saliency for Context Explanations of Semantic Segmentationcited by 32
  31. 2020Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instancescited by 31
  32. 2019Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentationcited by 18
  33. 2019Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentationcited by 17
  34. 2018Robust Tumor Localization with Pyramid Grad-CAMcited by 13
  35. 2019Budget-aware Semi-Supervised Semantic and Instance Segmentationcited by 11
  36. 2019Instance Segmentation with Point Supervisioncited by 8
  37. 2018Weakly Supervised Instance Segmentation Using Hybrid Networkcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 26; 2023: 29; 2024: 25; 2025: 7; 2026: 5.

104 papers.

Sort:

By area:

  1. 2023DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Modelscited by 162
  2. 2022Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformerscited by 118
  3. 2022Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentationcited by 87
  4. 2021Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labelingcited by 84
  5. 2021Reducing Information Bottleneck for Weakly Supervised Semantic Segmentationcited by 65
  6. 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
  7. 2023Token Contrast for Weakly-Supervised Semantic Segmentationcited by 64
  8. 2023A Comprehensive Survey on Segment Anything Model for Vision and Beyondcited by 64
  9. 2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
  10. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  11. 2023Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentationcited by 53
  12. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
38 more
  1. 2022Box-supervised Instance Segmentation with Level Set Evolutioncited by 41
  2. 2022Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentationcited by 37
  3. 2022BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentationcited by 31
  4. 2023Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentationcited by 27
  5. 2021CDGNet: Class Distribution Guided Network for Human Parsingcited by 26
  6. 2022Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentationcited by 26
  7. 2021Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinementcited by 25
  8. 2022SATS: Self-Attention Transfer for Continual Semantic Segmentationcited by 24
  9. 2022FedMix: Mixed Supervised Federated Learning for Medical Image Segmentationcited by 22
  10. 2022Box2Mask: Box-supervised Instance Segmentation via Level-set Evolutioncited by 22
  11. 2023WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentationcited by 22
  12. 2022Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?cited by 21
  13. 2023The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representationcited by 21
  14. 2021Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Imagescited by 20
  15. 2023Mask-Free Video Instance Segmentationcited by 20
  16. 2024Interpreting Object-level Foundation Models via Visual Precision Searchcited by 20
  17. 2022Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Poolingcited by 19
  18. 2023An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problemscited by 19
  19. 2023Weakly-Supervised Semantic Segmentation with Image-Level Labels: from Traditional Models to Foundation Modelscited by 19
  20. 2021Generative Transformer for Accurate and Reliable Salient Object Detectioncited by 18
  21. 2021Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teachingcited by 18
  22. 2024DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentationcited by 17
  23. 2023Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotationscited by 16
  24. 2023Semantic-aware SAM for Point-Prompted Instance Segmentationcited by 16
  25. 2024Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentationcited by 16
  26. 2022TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervisioncited by 15
  27. 2024Adaptive Patch Contrast for Weakly Supervised Semantic Segmentationcited by 15
  28. 2024Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentationcited by 14
  29. 2022Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localizationcited by 12
  30. 2023ODAM: Gradient-based instance-specific visual explanations for object detectioncited by 12
  31. 2024Learning Camouflaged Object Detection from Noisy Pseudo Labelcited by 12
  32. 2022Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaborationcited by 11
  33. 2023SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentationcited by 11
  34. 2022LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Drivingcited by 9
  35. 2024WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognitioncited by 9
  36. 2024Toward Interactive Regional Understanding in Vision-Large Language Modelscited by 9
  37. 2024MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentationcited by 9
  38. 2021GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentationcited by 8

50 most cited of 104 All 104 (JSON)