# P2Seg: Pointly-supervised Segmentation via Mutual Distillation

arXiv: https://arxiv.org/abs/2401.09709 · HTML: https://mlsanity.com/paper/2401.09709/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 18 Jan 2024.

## Builds on (most cited first, 30 of 34)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [Combating noisy labels by agreement: A joint training method with co-regularization](https://mlsanity.com/paper/2003.02752/) (2020)
- [Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations](https://mlsanity.com/paper/1904.05044/) (2019)
- [Multi-scale Interactive Network for Salient Object Detection](https://mlsanity.com/paper/2007.09062/) (2020)
- [BoxInst: High-Performance Instance Segmentation with Box Annotations](https://mlsanity.com/paper/2012.02310/) (2020)
- [Regularizing Class-wise Predictions via Self-knowledge Distillation](https://mlsanity.com/paper/2003.13964/) (2020)
- [Multi-class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02891/) (2022)
- [Instance-aware Semantic Segmentation via Multi-task Network Cascades](https://mlsanity.com/paper/1512.04412/) (2015)
- [Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.02664/) (2022)
- [Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation](https://mlsanity.com/paper/1503.00848/) (2015)
- [Weakly Supervised Instance Segmentation using Class Peak Response](https://mlsanity.com/paper/1804.00880/) (2018)
- [Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.00962/) (2022)
- [L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2204.03206/) (2022)
- [InstanceCut: from Edges to Instances with MultiCut](https://mlsanity.com/paper/1611.08272/) (2016)
- [Convolutional Feature Masking for Joint Object and Stuff Segmentation](https://mlsanity.com/paper/1412.1283/) (2014)
- [Instance-sensitive Fully Convolutional Networks](https://mlsanity.com/paper/1603.08678/) (2016)
- [Object Counting and Instance Segmentation with Image-level Supervision](https://mlsanity.com/paper/1903.02494/) (2019)
- [Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances](https://mlsanity.com/paper/2007.09397/) (2020)
- [Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement](https://mlsanity.com/paper/2109.09477/) (2021)
- [Moonshine: Distilling with Cheap Convolutions](https://mlsanity.com/paper/1711.02613/) (2017)
- [Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport](https://mlsanity.com/paper/2308.01779/) (2023)
- [S4Net: Single Stage Salient-Instance Segmentation](https://mlsanity.com/paper/1711.07618/) (2017)
- [Semi-convolutional Operators for Instance Segmentation](https://mlsanity.com/paper/1807.10712/) (2018)

## 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.