Reproduce “MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Sanghyun Jo, In-Jae Yu, Kyungsu Kim

MARS filters weakly supervised segmentation pseudo-labels by comparing region features from an unsupervised semantic segmentation model with background regions across images. It then uses teacher predictions and uncertainty-weighted training to restore pixels removed by filtering. On PASCAL VOC 2012 validation, MARS reports 77.7% mean intersection-over-union, improving on segmentation baselines; it depends on masks and can confuse objects within categories.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.