Publication Type

Journal Article

Version

publishedVersion

Publication Date

4-2021

Abstract

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

Discipline

Information Security

Research Areas

Information Systems and Management

Publication

Neurocomputing

Volume

447

First Page

1

Last Page

9

ISSN

0925-2312

Identifier

10.1016/j.neucom.2021.02.093

Publisher

Elsevier

Additional URL

https://doi.org/10.1016/j.neucom.2021.02.093

Share

COinS