Region-based online selective examination for weakly supervised semantic segmentation
Lists
Only you see this
Abstract
Highlights•An online noise correction method for training segmentation models with noisy pseudo-labels.•A SAM-based region voting strategy for pixel-to-region aggregation.•A cross-view examination for adaptively correcting noisy pseudo-labels.•Our method achieves state-of-the-art performance on main benchmarks.
BibTeX
@article{chen2024region,
author = {Qi Chen and Yun Chen and Yuheng Huang and Xiaohua Xie and Lingxiao Yang},
title = {{Region-based online selective examination for weakly supervised semantic segmentation}},
journal = {Information Fusion},
year = {2024},
doi = {10.1016/j.inffus.2024.102311},
}Loading related content...