计算机科学
修剪
分割
人工智能
推论
卷积神经网络
背景(考古学)
机器学习
规范化(社会学)
模式识别(心理学)
农学
人类学
生物
社会学
古生物学
作者
Wei He,Meiqing Wu,Mingfu Liang,Siew-Kei Lam
标识
DOI:10.1109/wacv48630.2021.00100
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI