Refining pseudo-labels through iterative mix-up for weakly supervised semantic segmentation

Weakly supervised semantic segmentation (WSSS) aims to provide accurate pixel-level annotation based on only weak guidance, primarily derived from image-level labels. Recent WSSS methods exploit pseudo-labels generated from improved class activation maps (CAMs) to train a fine-grained classification...

Full description

Saved in:
Bibliographic Details
Main Authors: Yifan Wang, Kunhao Yuan, Gerald Schaefer, Xiyao Liu, Linglin Jing, Kehua Guo, James Wang, Hui Fang
Format: Default Article
Published: 2025
Subjects:
Engineering
Information and computing sciences
Computer vision and multimedia computation
Data management and data science
Information systems
Machine learning
weakly supervised semantic segmentation
class activation map
mixing methods
model-agnostic approach
Online Access:https://hdl.handle.net/2134/29237651.v1
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items