COSNet: A Novel Object Segmentation Network using Enhanced Boundaries in Cluttered Scenes
Ali, Muhammad Javaid, Mamoona Noman, Mubashir Fiaz, Mustansar Khan, Salman
Ali, Muhammad
Javaid, Mamoona
Noman, Mubashir
Fiaz, Mustansar
Khan, Salman
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Automated waste recycling aims to efficiently separate the recyclable objects from the waste by employing vision-based systems. However, the presence of varying shaped objects having different material types makes it a challenging problem, especially in cluttered environments. Existing segmentation methods perform reasonably on many semantic segmentation datasets by employing multi-contextual representations, however, their performance is degraded when utilized for waste object segmentation in cluttered scenarios. In addition, plastic objects further increase the complexity of the problem due to their translucent nature. To address these limitations, we introduce an efficacious segmentation network, named COSNet, that uses boundary cues along with multi-contextual information to accurately segment the objects in cluttered scenes. COSNet introduces novel components including feature sharpening block (FSB) and boundary enhancement module (BEM) for enhancing the features and highlighting the boundary information of irregular waste objects in cluttered environment. Extensive experiments on three challenging datasets including ZeroWaste-f [4], SpectralWaste [5], and ADE20K [50] demonstrate the effectiveness of the proposed method. Our COSNet achieves a significant gain of 1.8% on ZeroWaste-f and 2.1% on SpectralWaste datasets respectively in terms of mIoU metric. Source code is available at https://github.com/techmn/cosnet.
Citation
M. Ali, M. Javaid, M. Noman, M. Fiaz and S. Khan, "COSNet: A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered Scenes," 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA, 2025, pp. 1363-1372, doi: 10.1109/WACV61041.2025.00140.
Source
IEEE/CVF Winter Conference on Applications of Computer Vision, 2025
Conference
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025
Keywords
Semantic segmentation, Waste segmentation, Zerowaste, Spectralwaste, ADE20K, Feature enhancement, Background clutter
Subjects
Source
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025
Publisher
IEEE