Progressive channel-shrinking network

• المؤلفون الرئيسيون: Pan, Jianhong, Yang, Siyuan, Foo, Lin Geng, Ke, Qiuhong, Rahmani, Hossein, Fan, Zhipeng, Liu, Jun
• مؤلفون آخرون: Interdisciplinary Graduate School (IGS)
• التنسيق: مقال
• اللغة: English
• منشور في: 2023
• الموضوعات: Engineering::Computer science and engineering; Progressive; Network Shrinking
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/171831

Currently, salience-based channel pruning makes continuous breakthroughs in network compression. In the realization, the salience mechanism is used as a metric of channel salience to guide pruning. Therefore, salience-based channel pruning can dynamically adjust the channel width at run-time, which provides a flexible pruning scheme. However, there are two problems emerging: a gating function is often needed to truncate the specific salience entries to zero, which destabilizes the forward propagation; dynamic architecture brings more cost for indexing in inference which bottlenecks the inference speed. In this paper, we propose a Progressive Channel-Shrinking (PCS) method to compress the selected salience entries at run-time instead of roughly approximating them to zero. We also propose a Running Shrinking Policy to provide a testing-static pruning scheme that can reduce the memory access cost for filter indexing. We evaluate our method on ImageNet and CIFAR10 datasets over two prevalent networks: ResNet and VGG, and demonstrate that our PCS outperforms all baselines and achieves state-of-the-art in terms of compression-performance tradeoff. Moreover, we observe a significant and practical acceleration of inference. The code will be released upon acceptance.