SOTAVerified

SLAMs: Semantic Learning based Activation Map for Weakly Supervised Semantic Segmentation

2022-10-22Unverified0· sign in to hype

Junliang Chen, Xiaodong Zhao, Minmin Liu, Linlin Shen

Unverified — Be the first to reproduce this paper.

Reproduce

Abstract

Recent mainstream weakly-supervised semantic segmentation (WSSS) approaches mainly relies on image-level classification learning, which has limited representation capacity. In this paper, we propose a novel semantic learning based framework, named SLAMs (Semantic Learning based Activation Map), for WSSS.

Tasks

Reproductions