mlsanityData to 7 Oct 2026

P2Seg: Pointly-supervised Segmentation via Mutual Distillation

arXiv 2401.09709 ↗First posted 18 Jan 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Point-level Supervised Instance Segmentation (PSIS) aims to enhance the applicability and scalability of instance segmentation by utilizing low-cost yet instance-informative annotations. Existing PSIS methods usually rely on positional information to distinguish objects, but predicting precise boundaries remains challenging due to the lack of contour annotations. Nevertheless, weakly supervised semantic segmentation methods are proficient in utilizing intra-class feature consistency to capture the boundary contours of the same semantic regions. In this paper, we design a Mutual Distillation Module (MDM) to leverage the complementary strengths of both instance position and semantic information and achieve accurate instance-level object perception. The MDM consists of Semantic to Instance (S2I) and Instance to Semantic (I2S). S2I is guided by the precise boundaries of semantic regions to learn the association between annotated points and instance contours. I2S leverages discriminative relationships between instances to facilitate the differentiation of various objects within the semantic map. Extensive experiments substantiate the efficacy of MDM in fostering the synergy between instance and semantic information, consequently improving the quality of instance-level object representations. Our method achieves 55.7 mAP50 and 17.6 mAP on the PASCAL VOC and MS COCO datasets, significantly outperforming recent PSIS methods and several box-supervised instance segmentation competitors.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 18 Jan 2024.

Builds on

34 of 50 references.

References · 34

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2023Segment Anythingcited by 8,158
  4. 2017Mask R-CNNcited by 7,259
  5. 2017Decoupled Weight Decay Regularizationcited by 1,722
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2017Deep Mutual Learningcited by 621
  8. 2019Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillationcited by 491
  9. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  10. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 245
  11. 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
  12. 2020BoxInst: High-Performance Instance Segmentation with Box Annotationscited by 150
22 more
  1. 2020Regularizing Class-wise Predictions via Self-knowledge Distillationcited by 144
  2. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  3. 2015Instance-aware Semantic Segmentation via Multi-task Network Cascadescited by 120
  4. 2022Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformerscited by 118
  5. 2015Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generationcited by 90
  6. 2022Class Re-Activation Maps for Weakly-Supervised Semantic Segmentationcited by 75
  7. 2018Weakly Supervised Instance Segmentation using Class Peak Responsecited by 74
  8. 2022L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentationcited by 57
  9. 2016InstanceCut: from Edges to Instances with MultiCutcited by 48
  10. 2014Convolutional Feature Masking for Joint Object and Stuff Segmentationcited by 41
  11. 2016Instance-sensitive Fully Convolutional Networkscited by 36
  12. 2019Object Counting and Instance Segmentation with Image-level Supervisioncited by 35
  13. 2020Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instancescited by 31
  14. 2021Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinementcited by 25
  15. 2017Moonshine: Distilling with Cheap Convolutionscited by 23
  16. 2017S4Net: Single Stage Salient-Instance Segmentationcited by 23
  17. 2023Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transportcited by 23
  18. 2018Semi-convolutional Operators for Instance Segmentationcited by 21
  19. 2018Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networkscited by 19
  20. 2019Where are the Masks: Instance Segmentation with Image-level Supervisioncited by 18
  21. 2019Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentationcited by 17
  22. 2021MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurationscited by 12

Built on by

Not cited yet.