瓶颈
块(置换群论)
冗余(工程)
计算机科学
极限(数学)
方块设计
频道(广播)
理论计算机科学
算法
数学
计算机网络
嵌入式系统
数学分析
几何学
组合数学
操作系统
出处
期刊:Cornell University - arXiv
日期:2022-01-01
被引量:5
标识
DOI:10.48550/arxiv.2203.06589
摘要
As a remarkable compact model, ShuffleNetV2 offers a good example to design efficient ConvNets but its limit is rarely noticed. In this paper, we rethink the design pattern of ShuffleNetV2 and find that the channel-wise redundancy problem still constrains the efficiency improvement of Shuffle block in the wider ShuffleNetV2. To resolve this issue, we propose another augmented variant of shuffle block in the form of bottleneck-like structure and more implicit short connections. To verify the effectiveness of this building block, we further build a more powerful and efficient model family, termed as AugShuffleNets. Evaluated on the CIFAR-10 and CIFAR-100 datasets, AugShuffleNet consistently outperforms ShuffleNetV2 in terms of accuracy with less computational cost and fewer parameter count.
科研通智能强力驱动
Strongly Powered by AbleSci AI