CVOct 22, 2022
SLAMs: Semantic Learning based Activation Map for Weakly Supervised Semantic Segmentation
arXiv:2210.12417v2h-index: 36
Originality Synthesis-oriented
AI Analysis
This addresses weakly-supervised semantic segmentation for computer vision, but appears incremental as it builds on existing classification-based approaches.
The paper tackles the limited representation capacity of image-level classification in weakly-supervised semantic segmentation by proposing SLAMs, a semantic learning based activation map framework, but no concrete results or numbers are provided in the 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.