{"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/non-local-neural-networks-with-grouped","title":"Non-Local Neural Networks With Grouped Bilinear Attentional Transforms","arxiv_id":null,"date":"2020-06-01","proceeding":"CVPR 2020 6","authors":["Lu Chi"," Zehuan Yuan"," Yadong Mu"," Changhu Wang"],"abstract":"Modeling spatial or temporal long-range dependency plays a key role in deep neural networks. Conventional dominant solutions include recurrent operations on sequential data or deeply stacking convolutional layers with small kernel size. Recently, a number of non-local operators (such as self-attention based) have been devised. They are typically generic and can be plugged into many existing network pipelines for globally computing among any two neurons in a feature map. This work proposes a novel non-local operator. It is inspired by the attention mechanism of human visual system, which can quickly attend to important local parts in sight and suppress other less-relevant information. The core of our method is learnable and data-adaptive bilinear attentional transform (BA-Transform), whose merits are three-folds: first, BA-Transform is versatile to model a wide spectrum of local or global attentional operations, such as emphasizing specific local regions. Each BA-Transform is learned in a data-adaptive way; Secondly, to address the discrepancy among features, we further design grouped BA-Transforms, which essentially apply different attentional operations to different groups of feature channels; Thirdly, many existing non-local operators are computation-intensive. The proposed BA-Transform is implemented by simple matrix multiplication and admits better efficacy. For empirical evaluation, we perform comprehensive experiments on two large-scale benchmarks, ImageNet and Kinetics, for image / video classification respectively. The achieved accuracies and various ablation experiments consistently demonstrate significant improvement by large margins.\r","url_abs":"http://openaccess.thecvf.com/content_CVPR_2020/html/Chi_Non-Local_Neural_Networks_With_Grouped_Bilinear_Attentional_Transforms_CVPR_2020_paper.html","url_pdf":"http://openaccess.thecvf.com/content_CVPR_2020/papers/Chi_Non-Local_Neural_Networks_With_Grouped_Bilinear_Attentional_Transforms_CVPR_2020_paper.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":"non-local-neural-networks-with-grouped","repo_url":"https://github.com/BA-Transform/BAT-Image-Classification","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"non-local-neural-networks-with-grouped","repo_url":"https://github.com/BA-Transform/BAT-Video-Classification","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"non-local-neural-networks-with-grouped","repo_url":"https://github.com/rwightman/pytorch-image-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"video-classification","task_name":"Video Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}