CBAM: Convolutional Block Attention Module

Abstract

We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, our module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement. Because CBAM is a lightweight and general module, it can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs. We validate our CBAM through extensive experiments on ImageNet-1K, MS~COCO detection, and VOC~2007 detection datasets. Our experiments show consistent improvements in classification and detection performances with various models, demonstrating the wide applicability of CBAM. The code and models will be publicly available.

Accepted to ECCV 2018

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Wide Residual Networks
• Going Deeper with Convolutions
• Recurrent Models of Visual Attention
• Xception: Deep Learning with Depthwise Separable Convolutions
• Residual Attention Network for Image Classification

Cited by in corpus (36)

• ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images
• Cross-Modality Deep Feature Learning for Brain Tumor Segmentation
• Improving prediction of the terrestrial water storage anomalies during the GRACE and GRACE-FO gap with Bayesian convolutional neural networks
• Selective Kernel Networks
• Identity-Guided Human Semantic Parsing for Person Re-Identification
• TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices
• Sequential Image-based Attention Network for Inferring Force Estimation without Haptic Sensor
• Lightweight Convolutional Neural Network with Gaussian-based Grasping Representation for Robotic Grasping Detection
• Joint Iris Segmentation and Localization Using Deep Multi-task Learning Framework
• Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
• Self-training with noisy student model and semi-supervised loss function for dcase 2021 challenge task 4
• Compact Global Descriptor for Neural Networks
• 3DVSR: 3D EPI Volume-based Approach for Angular and Spatial Light field Image Super-resolution
• AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers
• BAM: A Balanced Attention Mechanism for Single Image Super Resolution
• STRIDE : Scene Text Recognition In-Device
• Residual Convolutional Neural Network Revisited with Active Weighted Mapping
• Dual Attention GANs for Semantic Image Synthesis
• Multi-phase Liver Tumor Segmentation with Spatial Aggregation and Uncertain Region Inpainting
• Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution
• Multi-Level Attentive Convoluntional Neural Network for Crowd Counting
• Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving
• Learning To Pay Attention To Mistakes
• Iris Presentation Attack Detection by Attention-based and Deep Pixel-wise Binary Supervision Network
• Sharpen Focus: Learning with Attention Separability and Consistency
• Dense Prediction with Attentive Feature Aggregation
• Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism
• Ranking-Based Autoencoder for Extreme Multi-label Classification
• CDGNet: Class Distribution Guided Network for Human Parsing
• Multiple Myeloma Cancer Cell Instance Segmentation
• Multi-QuartzNet: Multi-Resolution Convolution for Speech Recognition with Multi-Layer Feature Fusion
• Class Activation Map generation by Multiple Level Class Grouping and Orthogonal Constraint
• Image-based Vehicle Re-identification Model with Adaptive Attention Modules and Metadata Re-ranking
• Multi-Scale Hourglass Hierarchical Fusion Network for Single Image Deraining
• Fine-grained MRI Reconstruction using Attentive Selection Generative Adversarial Networks
• Careful analysis of XRD patterns with Attention