Weakly supervised segmentation via instance-aware propagation
| Autor: | Yongtuo Liu, Xin Huang, Qianshu Zhu, Shengfeng He |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
0209 industrial biotechnology
Class (computer programming) business.industry Computer science Cognitive Neuroscience 02 engineering and technology Filter (signal processing) Pascal (programming language) Machine learning computer.software_genre Object (computer science) Computer Science Applications Constraint (information theory) 020901 industrial engineering & automation Discriminative model Artificial Intelligence 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Cover (algebra) Artificial intelligence business computer computer.programming_language |
| Zdroj: | Neurocomputing. 447:1-9 |
| ISSN: | 0925-2312 |
| DOI: | 10.1016/j.neucom.2021.02.093 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect