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

TL;DR

This paper introduces SLAMs, a novel framework for weakly-supervised semantic segmentation that enhances representation capacity beyond traditional classification-based methods.

Contribution

SLAMs leverages semantic learning to generate more accurate activation maps, improving weakly-supervised segmentation performance.

Findings

SLAMs outperforms existing WSSS methods in accuracy.

Semantic learning enhances activation map quality.

The framework demonstrates robustness across datasets.

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.