Multi-scale spatial pyramid attention mechanism for image recognition: An effective approach

计算机科学 棱锥(几何) 判别式 人工智能 卷积神经网络 瓶颈 残余物 卷积(计算机科学) 架空(工程) 特征(语言学) 模式识别(心理学) 人工神经网络 算法 嵌入式系统 操作系统 语言学 光学 物理 哲学
作者
Yu Yang,Yi Zhang,Zeyu Cheng,Zhe Song,Chengkai Tang
出处
期刊:Engineering Applications of Artificial Intelligence [Elsevier BV]
卷期号:133: 108261-108261 被引量:11
标识
DOI:10.1016/j.engappai.2024.108261
摘要

Attention mechanisms have gradually become necessary to enhance the representational power of convolutional neural networks (CNNs). Despite recent progress in attention mechanism research, some open problems still exist. Most existing methods ignore modeling multi-scale feature representations, structural information, and long-range channel dependencies, which are essential for delivering more discriminative attention maps. This study proposes a novel, low-overhead, high-performance attention mechanism with strong generalization ability for various networks and datasets. This mechanism is called Multi-Scale Spatial Pyramid Attention (MSPA) and can be used to solve the limitations of other attention methods. For the critical components of MSPA, we not only develop the Hierarchical-Phantom Convolution (HPC) module, which can extract multi-scale spatial information at a more granular level utilizing hierarchical residual-like connections, but also design the Spatial Pyramid Recalibration (SPR) module, which can integrate structural regularization and structural information in an adaptive combination mechanism, while employing the Softmax operation to build long-range channel dependencies. The proposed MSPA is a powerful tool that can be conveniently embedded into various CNNs as a plug-and-play component. Correspondingly, using MSPA to replace the 3 × 3 convolution in the bottleneck residual blocks of ResNets, we created a series of simple and efficient backbones named MSPANet, which naturally inherit the advantages of MSPA. Without bells and whistles, our method substantially outperforms other state-of-the-art counterparts in all evaluation metrics based on extensive experimental results from CIFAR-100 and ImageNet-1K image recognition. When applying MSPA to ResNet-50, our model achieves top-1 classification accuracy of 81.74% and 78.40% on the CIFAR-100 and ImageNet-1K benchmarks, exceeding the corresponding baselines by 3.95% and 2.27%, respectively. We also obtained promising performance improvements of 1.15% and 0.91% compared to the competitive EPSANet-50. In addition, empirical research results in autonomous driving engineering applications also demonstrate that our method can significantly improve the accuracy and real-time performance of image recognition with cheaper overhead. Our code is publicly available at https://github.com/ndsclark/MSPANet.
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
2秒前
NiNi完成签到,获得积分10
3秒前
Ther完成签到,获得积分20
4秒前
傲娇白安完成签到,获得积分10
5秒前
5秒前
甜蜜的荟完成签到,获得积分20
6秒前
婷儿完成签到,获得积分10
6秒前
牛牛发布了新的文献求助10
6秒前
Hoper完成签到,获得积分10
6秒前
张曰淼完成签到,获得积分10
7秒前
共渡完成签到,获得积分10
9秒前
凉白开完成签到 ,获得积分10
10秒前
跳跃的太君完成签到,获得积分10
11秒前
小猪发布了新的文献求助10
11秒前
独特问夏完成签到,获得积分10
12秒前
12秒前
13秒前
魔幻蓉完成签到,获得积分10
13秒前
杠赛来完成签到,获得积分10
13秒前
ccy完成签到 ,获得积分10
14秒前
Ch185完成签到,获得积分10
15秒前
欣喜的复天完成签到,获得积分10
17秒前
摸鱼校尉完成签到,获得积分0
17秒前
双儿完成签到,获得积分10
17秒前
顺利毕业完成签到 ,获得积分10
17秒前
儒雅的焦完成签到 ,获得积分10
17秒前
小何完成签到 ,获得积分10
17秒前
19秒前
20秒前
小曾应助张绪帆采纳,获得10
20秒前
麻麻薯完成签到 ,获得积分10
21秒前
21秒前
Smes完成签到,获得积分10
21秒前
王金豪发布了新的文献求助10
22秒前
勤劳冰烟完成签到,获得积分10
22秒前
顺顺尼完成签到 ,获得积分10
23秒前
24秒前
阿曾发布了新的文献求助10
25秒前
25秒前
鹤昀完成签到 ,获得积分10
26秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
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 4038368
求助须知:如何正确求助?哪些是违规求助? 3576068
关于积分的说明 11374313
捐赠科研通 3305780
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029