Spatial Attention Module

Introduced by Woo et al. in CBAM: Convolutional Block Attention Module

A Spatial Attention Module is a module for spatial attention in convolutional neural networks. It generates a spatial attention map by utilizing the inter-spatial relationship of features. Different from the channel attention, the spatial attention focuses on where is an informative part, which is complementary to the channel attention. To compute the spatial attention, we first apply average-pooling and max-pooling operations along the channel axis and concatenate them to generate an efficient feature descriptor. On the concatenated feature descriptor, we apply a convolution layer to generate a spatial attention map $\textbf{M}_{s}\left(F\right) \in \mathcal{R}^{H×W}$ which encodes where to emphasize or suppress.

We aggregate channel information of a feature map by using two pooling operations, generating two 2D maps: $\mathbf{F}^{s}_{avg} \in \mathbb{R}^{1\times{H}\times{W}}$ and $\mathbf{F}^{s}_{max} \in \mathbb{R}^{1\times{H}\times{W}}$. Each denotes average-pooled features and max-pooled features across the channel. Those are then concatenated and convolved by a standard convolution layer, producing the 2D spatial attention map. In short, the spatial attention is computed as:

$$ \textbf{M}_{s}\left(F\right) = \sigma\left(f^{7x7}\left(\left[\text{AvgPool}\left(F\right);\text{MaxPool}\left(F\right)\right]\right)\right) $$

$$ \textbf{M}_{s}\left(F\right) = \sigma\left(f^{7x7}\left(\left[\mathbf{F}^{s}_{avg};\mathbf{F}^{s}_{max} \right]\right)\right) $$

where $\sigma$ denotes the sigmoid function and $f^{7×7}$ represents a convolution operation with the filter size of 7 × 7.

Source: CBAM: Convolutional Block Attention Module

Latest Papers

PAPER DATE
Scaled-YOLOv4: Scaling Cross Stage Partial Network
| Chien-Yao WangAlexey BochkovskiyHong-Yuan Mark Liao
2020-11-16
Real-Time Polyp Detection, Localisation and Segmentation in Colonoscopy Using Deep Learning
Debesh JhaSharib AliHåvard D. JohansenDag D. JohansenJens RittscherMichael A. RieglerPål Halvorsen
2020-11-15
Real-time object detection method based on improved YOLOv4-tiny
Zicong JiangLiquan ZhaoShuaiyang LiYanfei Jia
2020-11-09
Detecting soccer balls with reduced neural networks: a comparison of multiple architectures under constrained hardware scenarios
Douglas De Rizzo MeneghettiThiago Pedro Donadon HomemJonas Henrique Renolfi de OliveiraIsaac Jesus da SilvaDanilo Hernani PericoReinaldo Augusto da Costa Bianchi
2020-09-28
CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation
Ran GuGuotai WangTao SongRui HuangMichael AertsenJan DeprestSébastien OurselinTom VercauterenShaoting Zhang
2020-09-22
YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design
Yuxuan CaiHongjia LiGeng YuanWei NiuYanyu LiXulong TangBin RenYanzhi Wang
2020-09-12
Dual Attention GANs for Semantic Image Synthesis
| Hao TangSong BaiNicu Sebe
2020-08-29
Alleviating Human-level Shift : A Robust Domain Adaptation Method for Multi-person Pose Estimation
| Xixia XuQi ZouXue Lin
2020-08-13
Object Detection and Tracking Algorithms for Vehicle Counting: A Comparative Analysis
Vishal MandalYaw Adu-Gyamfi
2020-07-31
Multimodal Spatial Attention Module for Targeting Multimodal PET-CT Lung Tumor Segmentation
Xiaohang FuLei BiAshnil KumarMichael FulhamJinman Kim
2020-07-29
PP-YOLO: An Effective and Efficient Implementation of Object Detector
| Xiang LongKaipeng DengGuanzhong WangYang ZhangQingqing DangYuan GaoHui ShenJianguo RenShumin HanErrui DingShilei Wen
2020-07-23
Face Super-Resolution Guided by 3D Facial Priors
Xiaobin HuWenqi RenJohn LaMasterXiaochun CaoXiaoming LiZechao LiBjoern MenzeWei Liu
2020-07-18
EndoSLAM Dataset and An Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearner
| Kutsev Bengisu OzyorukGuliz Irem GokcelerGulfize CoskunKagan IncetanYasin AlmaliogluFaisal MahmoodEva CurtoLuis PerdigotoMarina OliveiraHasan SahinHelder AraujoHenrique AlexandrinoNicholas J. DurrHunter B. GilbertMehmet Turan
2020-06-30
Correlation-Guided Attention for Corner Detection Based Visual Tracking
Fei Du Peng Liu Wei Zhao Xianglong Tang
2020-06-01
Attention-based network for low-light image enhancement
Cheng ZhangQingsen YanYu zhuXianjun LiJinqiu SunYanning Zhang
2020-05-20
YOLOv4: Optimal Speed and Accuracy of Object Detection
| Alexey BochkovskiyChien-Yao WangHong-Yuan Mark Liao
2020-04-23
SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation
| Changlu GuoMárton SzemenyeiYugen YiWenle WangBuer ChenChangqi Fan
2020-04-07
Learning Oracle Attention for High-fidelity Face Completion
Tong ZhouChangxing DingShaowen LinXinchao WangDacheng Tao
2020-03-31
Context-Aware Domain Adaptation in Semantic Segmentation
Jinyu YangWeizhi AnChaochao YanPeilin ZhaoJunzhou Huang
2020-03-09
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
| Chien-Yao WangHong-Yuan Mark LiaoI-Hau YehYueh-Hua WuPing-Yang ChenJun-Wei Hsieh
2019-11-27
ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices
Zheng Qin Zeming Li Zhaoning Zhang Yiping Bao Gang Yu Yuxing Peng Jian Sun
2019-10-01
Point Attention Network for Semantic Segmentation of 3D Point Clouds
Mingtao FengLiang ZhangXuefei LinSyed Zulqarnain GilaniAjmal Mian
2019-09-27
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
Minghui LiaoPengyuan LyuMinghang HeCong YaoWenhao WuXiang Bai
2019-08-22
HA-CCN: Hierarchical Attention-based Crowd Counting Network
Vishwanath A. SindagiVishal M. Patel
2019-07-24
Image Super-Resolution Using Attention Based DenseNet with Residual Deconvolution
Zhuangzi Li
2019-07-03
ThunderNet: Towards Real-time Generic Object Detection
| Zheng QinZeming LiZhaoning ZhangYiping BaoGang YuYuxing PengJian Sun
2019-03-28
Online Multi-Object Tracking with Dual Matching Attention Networks
| Ji ZhuHua YangNian LiuMinyoung KimWenjun ZhangMing-Hsuan Yang
2019-02-02
Sequential Image-based Attention Network for Inferring Force Estimation without Haptic Sensor
| Hochul ShinHyeon ChoDongyi KimDaekwan KoSoochul LimWonjun Hwang
2018-11-17
CBAM: Convolutional Block Attention Module
| Sanghyun WooJongchan ParkJoon-Young LeeIn So Kweon
2018-07-17
Residual Attention Network for Image Classification
| Fei WangMengqing JiangChen QianShuo YangCheng LiHonggang ZhangXiaogang WangXiaoou Tang
2017-04-23

Categories