Activation extending based on long-range dependencies for weakly supervised semantic segmentation.
Weakly supervised semantic segmentation (WSSS) principally obtains pseudo-labels based on the class activation maps (CAM) to handle expensive annotation resources. However, CAM easily involves false and local activation due to the the lack of annotation information. This paper suggests weakly superv...
Main Authors: | Haipeng Liu, Yibo Zhao, Meng Wang, Meiyan Ma, Zhaoyu Chen |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2023-01-01
|
Series: | PLoS ONE |
Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0288596&type=printable |
Similar Items
-
Activation extending based on long-range dependencies for weakly supervised semantic segmentation
by: Haipeng Liu, et al.
Published: (2023-01-01) -
Rethinking CAM in Weakly-Supervised Semantic Segmentation
by: Yuqi Song, et al.
Published: (2022-01-01) -
Extracting Structured Supervision From Captions for Weakly Supervised Semantic Segmentation
by: Daniel R. Vilar, et al.
Published: (2021-01-01) -
Learning graph structures with transformer for weakly supervised semantic segmentation
by: Wanchun Sun, et al.
Published: (2023-07-01) -
Polarized Attention Weak Supervised Semantic Segmentation Network
by: Min Dai, et al.
Published: (2024-01-01)