Weakly supervised segmentation via instance-aware propagation
Peak Response Map (PRM) highlighting the discriminative regions can be extracted from a pre-trained classification network. We can accurately localize instances of each class with the help of these response maps. However, these maps cannot provide reliable information for segmentation even with off-...
Saved in:
Main Authors: | XIN, Huang, ZHU, Qianshu, LIU, Yongtuo, HE, Shengfeng |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7843 https://ink.library.smu.edu.sg/context/sis_research/article/8846/viewcontent/weakly.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Semi-supervised tooth instance segmentation
by: Ling, Zijie
Published: (2024) -
Unbiased multiple instance learning for weakly supervised video anomaly detection
by: Lv, Hui, et al.
Published: (2023) -
Weakly-supervised semantic segmentation
by: CHEN, Zhaozheng
Published: (2023) -
Representative discovery of structure cues for weakly-supervised image segmentation
by: ZHANG, Luming, et al.
Published: (2014) -
Class re-activation maps for weakly-supervised semantic segmentation
by: CHEN, Zhaozheng, et al.
Published: (2022)