.png){kind=icon}
Return
Weakly supervised segmentation via instance-aware propagation
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2021.02.093.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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-the-shelf object proposals. This is because neither PRM nor the proposals know which regions can be regarded as a complete instance. In this paper, we tackle this problem by proposing an Instance-aware Cue propagation Network (ICN) with a new proposal-matching strategy. In particular, the ICN aims to filter out background distractions and cover the complete instance, while our proposed proposal-matching strategy adds a re-balancing constraint on the contributions of multi-scale object proposals. Extensive experiments conducted on the PASCAL VOC 2012 dataset show the superior performance of our method over weakly-supervised state-of-the-arts for both semantic and instance segmentation. (c) 2021 Elsevier B.V. All rights reserved.
Keywords:
Weakly supervised learning
Instance segmentation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
Cited Papers
ShareSaveShareSaveDistribution, Source Identification, and Assessment of Potentially Toxic Elements in the Sediment Core from the Estuarine Region of the Golmud River to the Qarhan Salt Lake, Qinghai, China.png)
MineralsOAAI
MineralsIF0
OAAIShareSaveShareSaveShareSave
View more