mlsanityData to 7 Oct 2026

Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

arXiv 2104.01526 ↗First posted 4 Apr 2021cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based solution for weakly-supervised instance segmentation. The BoxCaseg model is jointly trained using box-supervised images and salient images in a multi-task learning manner. The fine-annotated salient images provide class-agnostic and precise object localization guidance for box-supervised images. The object masks predicted by a pretrained BoxCaseg model are refined via a novel merged and dropped strategy as proxy ground truth to train a Mask R-CNN for weakly-supervised instance segmentation. Only using 7991 salient images, the weakly-supervised Mask R-CNN is on par with fully-supervised Mask R-CNN on PASCAL VOC and significantly outperforms previous state-of-the-art box-supervised instance segmentation methods on COCO. The source code, pretrained models and datasets are available at urlhttps://github.com/hustvl/BoxCaseg.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 40 of its 59 references that are in the map. First posted on arXiv 4 Apr 2021.

Builds on

40 of 59 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Mask R-CNNcited by 7,259
  4. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  5. 2019PointRend: Image Segmentation as Renderingcited by 439
  6. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 410
  7. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  8. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  9. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 245
  10. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  11. 2019EGNet:Edge Guidance Network for Salient Object Detectioncited by 237
  12. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
28 more
  1. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  2. 2019Cascaded Partial Decoder for Fast and Accurate Salient Object Detectioncited by 216
  3. 2019A Simple Pooling-Based Design for Real-Time Salient Object Detectioncited by 211
  4. 2016Deeply supervised salient object detection with short connectionscited by 196
  5. 2015Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentationcited by 189
  6. 2020BoxInst: High-Performance Instance Segmentation with Box Annotationscited by 150
  7. 2015Salient Object Detection: A Benchmarkcited by 130
  8. 2018Reverse Attention for Salient Object Detectioncited by 113
  9. 2018Normalized Cut Loss for Weakly-supervised CNN Segmentationcited by 112
  10. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 104
  11. 2019Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentationcited by 97
  12. 2020Weakly-Supervised Salient Object Detection via Scribble Annotationscited by 96
  13. 2017Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detectioncited by 93
  14. 2015Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generationcited by 90
  15. 2014Salient Object Detection: A Discriminative Regional Feature Integration Approachcited by 89
  16. 2015Learning to Segment Object Candidatescited by 79
  17. 2018Weakly Supervised Instance Segmentation using Class Peak Responsecited by 74
  18. 2017Learning to Segment Every Thingcited by 64
  19. 2019Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentationcited by 57
  20. 2016Deep Contrast Learning for Salient Object Detectioncited by 52
  21. 2019Multi-source weak supervision for saliency detectioncited by 43
  22. 2019Object Counting and Instance Segmentation with Image-level Supervisioncited by 35
  23. 2018Weakly Supervised Salient Object Detection Using Image Labelscited by 32
  24. 2020Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instancescited by 31
  25. 2019Where are the Masks: Instance Segmentation with Image-level Supervisioncited by 18
  26. 2019Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentationcited by 17
  27. 2019Instance Segmentation with Point Supervisioncited by 8
  28. 2020Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentationcited by 4

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 5; 2023: 6; 2024: 5; 2025: 1.

20 papers.

Sort:

  1. 2021Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labelingcited by 84
  2. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
  3. 2022Box-supervised Instance Segmentation with Level Set Evolutioncited by 41
  4. 2022BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentationcited by 31
  5. 2022Box2Mask: Box-supervised Instance Segmentation via Level-set Evolutioncited by 22
  6. 2023BoxSnake: Polygonal Instance Segmentation with Box Supervisioncited by 12
  7. 2023SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentationcited by 11
  8. 2022LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Drivingcited by 9
  9. 2024WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognitioncited by 9
  10. 2021GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentationcited by 8
  11. 2024DAWN: Domain-Adaptive Weakly Supervised Nuclei Segmentation via Cross-Task Interactionscited by 8
  12. 2023MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Drivingcited by 5
8 more
  1. 2023ElC-OIS: Ellipsoidal Clustering for Open-World Instance Segmentation on LiDAR Datacited by 3
  2. 2024Extreme Point Supervised Instance Segmentationcited by 3
  3. 2023ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentationcited by 2
  4. 2024Boosting Box-supervised Instance Segmentation with Pseudo Depthcited by 2
  5. 2024PM-VIS: High-Performance Box-Supervised Video Instance Segmentationcited by 2
  6. 2025Towards Optimal Heterogeneous Client Sampling in Multi-Model Federated Learningcited by 1
  7. 2021Deep Level Set for Box-supervised Instance Segmentation in Aerial Imagescited by 0
  8. 2023BoxVIS: Video Instance Segmentation with Box Annotationscited by 0