{"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/part-based-r-cnns-for-fine-grained-category","title":"Part-based R-CNNs for Fine-grained Category Detection","arxiv_id":"1407.3867","date":"2014-07-15","proceeding":null,"authors":["Ning Zhang","Jeff Donahue","Ross Girshick","Trevor Darrell"],"abstract":"Semantic part localization can facilitate fine-grained categorization by\nexplicitly isolating subtle appearance differences associated with specific\nobject parts. Methods for pose-normalized representations have been proposed,\nbut generally presume bounding box annotations at test time due to the\ndifficulty of object detection. We propose a model for fine-grained\ncategorization that overcomes these limitations by leveraging deep\nconvolutional features computed on bottom-up region proposals. Our method\nlearns whole-object and part detectors, enforces learned geometric constraints\nbetween them, and predicts a fine-grained category from a pose-normalized\nrepresentation. Experiments on the Caltech-UCSD bird dataset confirm that our\nmethod outperforms state-of-the-art fine-grained categorization methods in an\nend-to-end evaluation without requiring a bounding box at test time.","url_abs":"http://arxiv.org/abs/1407.3867v1","url_pdf":"http://arxiv.org/pdf/1407.3867v1.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":[],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-cub-200","task":"Fine-Grained Image Classification","dataset":"CUB-200-2011","model":"Part RCNN","rank_in_archive_order":12,"of":12,"metrics":{"Accuracy":"76.4%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1407.3867","atlas_url":"https://app.syntology.ai/?focus=1407.3867","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}