# BAM: Bottleneck Attention Module

arXiv: https://arxiv.org/abs/1807.06514 · HTML: https://mlsanity.com/paper/1807.06514/

## Key facts

- Cited by 172 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2018.

## Built on by (most cited first, 30 of 172)

- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [CMT: Convolutional Neural Networks Meet Vision Transformers](https://mlsanity.com/paper/2107.06263/) (2021)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2103.10596/) (2021)
- [UIU-Net: U-Net in U-Net for Infrared Small Object Detection](https://mlsanity.com/paper/2212.00968/) (2022)
- [LambdaNetworks: Modeling Long-Range Interactions Without Attention](https://mlsanity.com/paper/2102.08602/) (2021)
- [Large Selective Kernel Network for Remote Sensing Object Detection](https://mlsanity.com/paper/2303.09030/) (2023)
- [On the Integration of Self-Attention and Convolution](https://mlsanity.com/paper/2111.14556/) (2021)
- [Omni Aggregation Networks for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2304.10244/) (2023)
- [Omni-Dimensional Dynamic Convolution](https://mlsanity.com/paper/2209.07947/) (2022)
- [Decoupled Dynamic Filter Networks](https://mlsanity.com/paper/2104.14107/) (2021)
- [RegNet: Self-Regulated Network for Image Classification](https://mlsanity.com/paper/2101.00590/) (2021)
- [BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification](https://mlsanity.com/paper/2104.14783/) (2021)
- [Transfer without Forgetting](https://mlsanity.com/paper/2206.00388/) (2022)
- [LSKNet: A Foundation Lightweight Backbone for Remote Sensing](https://mlsanity.com/paper/2403.11735/) (2024)
- [Polarized Self-Attention: Towards High-quality Pixel-wise Regression](https://mlsanity.com/paper/2107.00782/) (2021)
- [Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions](https://mlsanity.com/paper/2112.05561/) (2021)
- [ConTNet: Why not use convolution and transformer at the same time?](https://mlsanity.com/paper/2104.13497/) (2021)
- [Vision Transformers with Hierarchical Attention](https://mlsanity.com/paper/2106.03180/) (2021)
- [Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2110.05741/) (2021)
- [Event-guided Deblurring of Unknown Exposure Time Videos](https://mlsanity.com/paper/2112.06988/) (2021)
- [Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention](https://mlsanity.com/paper/2405.06284/) (2024)
- [Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition](https://mlsanity.com/paper/2209.14498/) (2022)
- [Subjective and Objective Quality Assessment for in-the-Wild Computer Graphics Images](https://mlsanity.com/paper/2303.08050/) (2023)
- [Attention in Attention Network for Image Super-Resolution](https://mlsanity.com/paper/2104.09497/) (2021)
- [EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network](https://mlsanity.com/paper/2105.14447/) (2021)
- [Challenges for machine learning in clinical translation of big data imaging studies](https://mlsanity.com/paper/2107.05630/) (2021)
- [Effective Image Tampering Localization via Enhanced Transformer and Co-attention Fusion](https://mlsanity.com/paper/2309.09306/) (2023)

## Abstract (arXiv)

Recent advances in deep neural networks have been developed via architecture search for stronger representational power. In this work, we focus on the effect of attention in general deep neural networks. We propose a simple and effective attention module, named Bottleneck Attention Module (BAM), that can be integrated with any feed-forward convolutional neural networks. Our module infers an attention map along two separate pathways, channel and spatial. We place our module at each bottleneck of models where the downsampling of feature maps occurs. Our module constructs a hierarchical attention at bottlenecks with a number of parameters and it is trainable in an end-to-end manner jointly with any feed-forward models. We validate our BAM through extensive experiments on CIFAR-100, ImageNet-1K, VOC 2007 and MS COCO benchmarks. Our experiments show consistent improvement in classification and detection performances with various models, demonstrating the wide applicability of BAM. The code and models will be publicly available.