BriefGPT.xyz
Sep, 2022
弱监督语义分割:渐进式补丁学习
Weakly Supervised Semantic Segmentation via Progressive Patch Learning
HTML
PDF
Jinlong Li, Zequn Jie, Xu Wang, Yu Zhou, Xiaolin Wei...
TL;DR
本文提出了一种新的渐进式补丁学习方法来提高弱监督语义分割中的局部细节提取,进一步将特征破坏和补丁学习扩展到多级粒度,同时与多阶段优化策略相结合来提供模型对不同程度的特征提取能力。此方法超越了大多数现有的弱监督语义分割方法,在PASCAL VOC 2012数据集上取得了出色的表现。
Abstract
Most of the existing
semantic segmentation
approaches with image-level class labels as supervision, highly rely on the initial class activation map (CAM) generated from the standard classification network. In this paper, a novel "
→