English

ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation

Computer Vision and Pattern Recognition 2023-08-01 v3

Abstract

We address a weakly-supervised low-shot instance segmentation, an annotation-efficient training method to deal with novel classes effectively. Since it is an under-explored problem, we first investigate the difficulty of the problem and identify the performance bottleneck by conducting systematic analyses of model components and individual sub-tasks with a simple baseline model. Based on the analyses, we propose ENInst with sub-task enhancement methods: instance-wise mask refinement for enhancing pixel localization quality and novel classifier composition for improving classification accuracy. Our proposed method lifts the overall performance by enhancing the performance of each sub-task. We demonstrate that our ENInst is 7.5 times more efficient in achieving comparable performance to the existing fully-supervised few-shot models and even outperforms them at times.

Keywords

Cite

@article{arxiv.2302.09765,
  title  = {ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation},
  author = {Moon Ye-Bin and Dongmin Choi and Yongjin Kwon and Junsik Kim and Tae-Hyun Oh},
  journal= {arXiv preprint arXiv:2302.09765},
  year   = {2023}
}

Comments

Accepted at Pattern Recognition (PR)