Please use this identifier to cite or link to this item:
Title: CAP : Context-aware Pruning for semantic segmentation
Authors: He, Wei
Wu, Meiqing
Liang, Mingfu
Lam, Siew-Kei 
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Issue Date: 2021
Source: He, W., Wu, M., Liang, M. & Lam, S. (2021). CAP : Context-aware Pruning for semantic segmentation. 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), 960-969.
Conference: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
Abstract: Network pruning for deep convolutional neural networks (CNNs) has recently achieved notable research progress on image-level classification. However, most existing pruning methods are not catered to or evaluated on semantic segmentation networks. In this paper, we advocate the importance of contextual information during channel pruning for semantic segmentation networks by presenting a novel Context-aware Pruning framework. Concretely, we formulate the embedded contextual information by leveraging the layer-wise channels interdependency via the Context-aware Guiding Module (CAGM) and introduce the Context-aware Guided Sparsification (CAGS) to adaptively identify the informative channels on the cumbersome model by inducing channel-wise sparsity on the scaling factors in batch normalization (BN) layers. The resulting pruned models require significantly lesser operations for inference while maintaining comparable performance to (at times outperforming) the original models. We evaluated our framework on widely-used benchmarks and showed its effectiveness on both large and lightweight models. On Cityscapes dataset, our framework reduces the number of parameters by 32%, 47%, 54%, and 63%, on PSPNet101, PSPNet50, ICNet, and SegNet, respectively, while preserving the performance.
Schools: School of Computer Science and Engineering 
Research Centres: Hardware & Embedded Systems Lab (HESL) 
Rights: © 2021 The Author(s) (published by IEEE). This is an open-access article distributed under the terms of the Creative Commons Attribution License.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Page view(s) 50

Updated on Jun 24, 2024

Download(s) 20

Updated on Jun 24, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.