{"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/attend-and-rectify-a-gated-attention","title":"Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery","arxiv_id":"1807.07320","date":"2018-07-19","proceeding":"ECCV 2018 9","authors":["Pau Rodríguez","Josep M. Gonfaus","Guillem Cucurull","F. Xavier Roca","Jordi Gonzàlez"],"abstract":"We propose a novel attention mechanism to enhance Convolutional Neural\nNetworks for fine-grained recognition. It learns to attend to lower-level\nfeature activations without requiring part annotations and uses these\nactivations to update and rectify the output likelihood distribution. In\ncontrast to other approaches, the proposed mechanism is modular,\narchitecture-independent and efficient both in terms of parameters and\ncomputation required. Experiments show that networks augmented with our\napproach systematically improve their classification accuracy and become more\nrobust to clutter. As a result, Wide Residual Networks augmented with our\nproposal surpasses the state of the art classification accuracies in CIFAR-10,\nthe Adience gender recognition task, Stanford dogs, and UEC Food-100.","url_abs":"http://arxiv.org/abs/1807.07320v2","url_pdf":"http://arxiv.org/pdf/1807.07320v2.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":"attend-and-rectify-a-gated-attention","repo_url":"https://github.com/prlz77/attend-and-rectify","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"WARN","rank_in_archive_order":108,"of":211,"metrics":{"Percentage correct":"82.18"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.07320","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}