# BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation

arXiv: https://arxiv.org/abs/2504.05137 · HTML: https://mlsanity.com/paper/2504.05137/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 60 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Builds on (most cited first, 5 of 5)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Optimize TSK Fuzzy Systems for Regression Problems: Mini-Batch Gradient Descent with Regularization, DropRule and AdaBound (MBGD-RDA)](https://mlsanity.com/paper/1903.10951/) (2019)
- [Deep Self-Supervised Representation Learning for Free-Hand Sketch](https://mlsanity.com/paper/2002.00867/) (2020)
- [Deep Ensemble Art Style Recognition](https://mlsanity.com/paper/2405.11675/) (2024)
- [Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement](https://mlsanity.com/paper/2103.06501/) (2021)

## Built on by (most cited first, 1 of 1)

- [Noise-Robust Box-Supervised Infrared Small Target Detection via Physics-Inspired Soft Label Optimization](https://mlsanity.com/paper/2607.17148/) (2026)

## Abstract (arXiv)

Box-supervised instance segmentation methods aim to achieve instance segmentation with only box annotations. Recent methods have demonstrated the effectiveness of acquiring high-quality pseudo masks under the teacher-student framework. Building upon this foundation, we propose a BoxSeg framework involving two novel and general modules named the Quality-Aware Module (QAM) and the Peer-assisted Copy-paste (PC). The QAM obtains high-quality pseudo masks and better measures the mask quality to help reduce the effect of noisy masks, by leveraging the quality-aware multi-mask complementation mechanism. The PC imitates Peer-Assisted Learning to further improve the quality of the low-quality masks with the guidance of the obtained high-quality pseudo masks. Theoretical and experimental analyses demonstrate the proposed QAM and PC are effective. Extensive experimental results show the superiority of our BoxSeg over the state-of-the-art methods, and illustrate the QAM and PC can be applied to improve other models.