DATran: Dual Attention Transformer for Multi-Label Image Classification

计算机科学 人工智能 模式识别(心理学) 利用 卷积神经网络 空间语境意识 图形 上下文图像分类 特征(语言学) 机器学习 图像(数学) 理论计算机科学 计算机安全 语言学 哲学
作者
Wei Zhou,Zhijie Zheng,Tao Su,Haifeng Hu
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology [Institute of Electrical and Electronics Engineers]
卷期号:34 (1): 342-356 被引量:1
标识
DOI:10.1109/tcsvt.2023.3284812
摘要

Multi-label image classification is a fundamental yet challenging task, which aims to predict the labels associated with a given image. Most of previous methods directly exploit the high-level features from the last layer of convolutional neural network for classification. However, these methods cannot obtain global features due to the limited size of convolutional kernels, and they fail to extract multi-scale features to effectively recognize small-scale objects in the images. Recent studies exploit the graph convolution network to model the label correlations for boosting the classification performance. Despite substantial progress, these methods rely on manually pre-defined graph structures. Besides, they ignore the associations between semantic labels and image regions, and do not fully explore the spatial context of images. To address above issues, we propose a novel Dual Attention Transformer (DATran) model, which adopts a dual-stream architecture that simultaneously learns spatial and channel correlations from multi-label images. Firstly, in order to solve the problem that current methods are difficult to recognize small-size objects, we develop a new multi-scale feature fusion (MSFF) module to generate multi-scale feature representation by jointly integrating both high-level semantics and low-level details. Secondly, we design a prior-enhanced spatial attention (PSA) module to learn the long-range correlation between objects from different spatial positions in images to enhance the model performance. Thirdly, we devise a prior-enhanced channel attention (PCA) module to capture the inter-dependencies between different channel maps, thus effectively improving the correlation between semantic categories. It is worth noting that PSA module and PCA module complement and promote each other to further augment the feature representations. Finally, the outputs of these two attention modules are fused to obtain the final features for classification. Performance evaluation experiments are conducted on MS-COCO 2014, PASCAL VOC 2007 and VG-500 datasets, demonstrating that DATran model achieves better performance than current state-of-the-art models.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
刚刚
3秒前
3秒前
3秒前
烟花应助飞起又落下采纳,获得10
5秒前
6秒前
6秒前
张军辉发布了新的文献求助10
8秒前
8秒前
wanglf发布了新的文献求助30
9秒前
悦耳的盼芙完成签到,获得积分10
9秒前
顾矜应助CC采纳,获得10
10秒前
Elijah完成签到,获得积分10
12秒前
声声慢完成签到 ,获得积分10
13秒前
14秒前
14秒前
14秒前
xiaoxin完成签到,获得积分20
15秒前
Owen应助懒羊羊大王采纳,获得10
17秒前
18秒前
Echizen完成签到,获得积分10
18秒前
19秒前
19秒前
一切随风完成签到,获得积分10
21秒前
开心完成签到,获得积分10
22秒前
xiaoxin发布了新的文献求助10
22秒前
23秒前
王艺霖发布了新的文献求助10
23秒前
在路上完成签到 ,获得积分10
23秒前
边渡有次子完成签到,获得积分10
26秒前
wanci应助老实的熊猫采纳,获得10
26秒前
默默的飞烟完成签到,获得积分10
27秒前
隐形鸣凤完成签到,获得积分10
30秒前
曲聋五完成签到 ,获得积分10
32秒前
嗯嗯嗯发布了新的文献求助10
32秒前
君子兰完成签到,获得积分10
33秒前
33秒前
我是老大应助lx33101128采纳,获得10
36秒前
小二郎应助白芷苏采纳,获得20
36秒前
38秒前
高分求助中
The late Devonian Standard Conodont Zonation 2000
Nickel superalloy market size, share, growth, trends, and forecast 2023-2030 2000
The Lali Section: An Excellent Reference Section for Upper - Devonian in South China 1500
Very-high-order BVD Schemes Using β-variable THINC Method 870
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 800
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
Development of general formulas for bolted flanges, by E.O. Waters [and others] 600
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3256413
求助须知:如何正确求助?哪些是违规求助? 2898688
关于积分的说明 8301838
捐赠科研通 2567805
什么是DOI,文献DOI怎么找? 1394718
科研通“疑难数据库(出版商)”最低求助积分说明 652913
邀请新用户注册赠送积分活动 630562