SA-Net: Shuffle Attention for Deep Convolutional Neural Networks

失败 计算机科学 架空(工程) 特征(语言学) 卷积神经网络 人工智能 成对比较 频道(广播) 光学(聚焦) 人工神经网络 目标检测 模式识别(心理学) 机器学习 深度学习 依赖关系(UML) 对象(语法) 计算机工程 并行计算 计算机网络 哲学 物理 光学 操作系统 语言学
作者
Qinglong Zhang,Yu-Bin Yang
标识
DOI:10.1109/icassp39728.2021.9414568
摘要

Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention mechanisms widely used in computer vision studies, spatial attention and channel attention, which aim to capture the pixel-level pairwise relationship and channel dependency, respectively. Although fusing them together may achieve better performance than their individual implementations, it will inevitably increase the computational overhead. In this paper, we propose an efficient Shuffle Attention (SA) module to address this issue, which adopts Shuffle Units to combine two types of attention mechanisms effectively. Specifically, SA first groups channel dimensions into multiple sub-features before processing them in parallel. Then, for each sub-feature, SA utilizes a Shuffle Unit to depict feature dependencies in both spatial and channel dimensions. After that, all sub-features are aggregated and a "channel shuffle" operator is adopted to enable information communication between different sub-features. The proposed SA module is efficient yet effective, e.g., the parameters and computations of SA against the backbone ResNet50 are 300 vs. 25.56M and 2.76e-3 GFLOPs vs. 4.12 GFLOPs, respectively, and the performance boost is more than 1.34% in terms of Top-1 accuracy. Extensive experimental results on common-used benchmarks, including ImageNet-1k for classification, MS COCO for object detection, and instance segmentation, demonstrate that the proposed SA outperforms the current SOTA methods significantly by achieving higher accuracy while having lower model complexity.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
mzhmhy发布了新的文献求助10
1秒前
李健的粉丝团团长应助ASA采纳,获得30
2秒前
Choi完成签到,获得积分0
2秒前
无辜如容发布了新的文献求助10
2秒前
123完成签到,获得积分10
3秒前
4秒前
单耳兔完成签到 ,获得积分10
4秒前
潇湘雪月发布了新的文献求助10
4秒前
故意的靳完成签到,获得积分10
6秒前
mzhmhy完成签到,获得积分10
6秒前
bkagyin应助wish采纳,获得10
10秒前
Afaq发布了新的文献求助10
10秒前
果粒多发布了新的文献求助10
11秒前
11秒前
无辜如容完成签到,获得积分10
12秒前
12秒前
15秒前
16秒前
ASA发布了新的文献求助30
16秒前
17秒前
情怀应助tingting9采纳,获得10
18秒前
FXQ123_范发布了新的文献求助10
18秒前
sun完成签到,获得积分20
18秒前
20秒前
彭于晏应助wldsd采纳,获得30
20秒前
量子星尘发布了新的文献求助10
20秒前
21秒前
21秒前
高一淼发布了新的文献求助10
22秒前
明道若昧完成签到,获得积分10
22秒前
上官若男应助mk采纳,获得10
23秒前
wish完成签到,获得积分10
25秒前
wish发布了新的文献求助10
27秒前
稍等一下完成签到 ,获得积分10
28秒前
momo发布了新的文献求助10
28秒前
30秒前
30秒前
liang白开完成签到,获得积分10
32秒前
mk发布了新的文献求助10
34秒前
丘比特应助嗯嗯采纳,获得10
34秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989263
求助须知:如何正确求助?哪些是违规求助? 3531418
关于积分的说明 11253814
捐赠科研通 3270066
什么是DOI,文献DOI怎么找? 1804884
邀请新用户注册赠送积分活动 882084
科研通“疑难数据库(出版商)”最低求助积分说明 809136