{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bam-bottleneck-attention-module","title":"BAM: Bottleneck Attention Module","arxiv_id":"1807.06514","date":"2018-07-17","proceeding":null,"authors":["Jongchan Park","Sanghyun Woo","Joon-Young Lee","In So Kweon"],"abstract":"Recent advances in deep neural networks have been developed via architecture\nsearch for stronger representational power. In this work, we focus on the\neffect of attention in general deep neural networks. We propose a simple and\neffective attention module, named Bottleneck Attention Module (BAM), that can\nbe integrated with any feed-forward convolutional neural networks. Our module\ninfers an attention map along two separate pathways, channel and spatial. We\nplace our module at each bottleneck of models where the downsampling of feature\nmaps occurs. Our module constructs a hierarchical attention at bottlenecks with\na number of parameters and it is trainable in an end-to-end manner jointly with\nany feed-forward models. We validate our BAM through extensive experiments on\nCIFAR-100, ImageNet-1K, VOC 2007 and MS COCO benchmarks. Our experiments show\nconsistent improvement in classification and detection performances with\nvarious models, demonstrating the wide applicability of BAM. The code and\nmodels will be publicly available.","url_abs":"http://arxiv.org/abs/1807.06514v2","url_pdf":"http://arxiv.org/pdf/1807.06514v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bam-bottleneck-attention-module","repo_url":"https://github.com/huyz1117/BAM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"bam-bottleneck-attention-module","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"bam-bottleneck-attention-module","repo_url":"https://github.com/xmu-xiaoma666/External-Attention-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"bam-bottleneck-attention-module","repo_url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/resnet50_bam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"bam-bottleneck-attention-module","repo_url":"https://github.com/2023-MindSpore-4/Code14/tree/main/resnet50_bam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"bam-bottleneck-attention-module","repo_url":"https://github.com/MindSpore-paper-code-3/code5/tree/main/resnet50_bam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"bam-bottleneck-attention-module","repo_url":"https://github.com/code-implementation1/Code7/tree/main/resnet50_bam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"bam-bottleneck-attention-module","repo_url":"https://github.com/gan3sh500/custom-pooling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"bam-bottleneck-attention-module","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/resnet50_bam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"bam-bottleneck-attention-module","repo_url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/BAM.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"bam","method_name":"BAM"}],"datasets_introduced":[],"methods_introduced":[{"slug":"bam","name":"BAM","full_name":"Bottleneck Attention Module"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.06514","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}