{"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/feature-channel-adaptive-enhancement-for-fine","title":"Feature Channel Adaptive Enhancement for Fine-Grained Visual Classification","arxiv_id":null,"date":"2023-05-11","proceeding":"The 7th Asian Conference on Pattern Recognition 2023 5","authors":["Dingzhou Xie","Cheng Pang","Guanhua Wu","Rushi Lan"],"abstract":"Fine-grained classification poses greater challenges compared\r\nto basic-level image classification due to the visually similar sub-species.\r\nTo distinguish between confusing species, we introduce a novel framework\r\nbased on feature channel adaptive enhancement and attention erasure.\r\nOn one hand, a lightweight module employing both channel attention\r\nand spatial attention is designed, adaptively enhancing the feature ex\u0002pression of important areas and obtaining more discriminative feature\r\nvectors. On the other hand, we incorporate attention erasure methods\r\nthat compel the network to concentrate on less prominent areas, thereby\r\nenhancing the network’s robustness. Our method can be seamlessly in\u0002tegrated into various backbone networks. Finally, an evaluation of our\r\napproach is conducted across diverse public datasets, accompanied by\r\na comprehensive comparative analysis against state-of-the-art method\u0002ologies. The experimental findings substantiate the efficacy and viability\r\nof our method in real-world scenarios, exemplifying noteworthy break\u0002throughs in intricate fine-grained classification endeavors.","url_abs":"https://link.springer.com/chapter/10.1007/978-3-031-47665-5_16","url_pdf":"https://link.springer.com/chapter/10.1007/978-3-031-47665-5_16","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":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"fine-grained-image-recognition","task_name":"Fine-Grained Image Recognition"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-recognition-on-cub-birds","task":"Fine-Grained Image Recognition","dataset":"CUB Birds","model":"Resnet50","rank_in_archive_order":2,"of":2,"metrics":{"1:1 Accuracy":"89.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}