{"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/grafit-learning-fine-grained-image","title":"Grafit: Learning fine-grained image representations with coarse labels","arxiv_id":"2011.12982","date":"2020-11-25","proceeding":"ICCV 2021 10","authors":["Hugo Touvron","Alexandre Sablayrolles","Matthijs Douze","Matthieu Cord","Hervé Jégou"],"abstract":"This paper tackles the problem of learning a finer representation than the one provided by training labels. This enables fine-grained category retrieval of images in a collection annotated with coarse labels only. Our network is learned with a nearest-neighbor classifier objective, and an instance loss inspired by self-supervised learning. By jointly leveraging the coarse labels and the underlying fine-grained latent space, it significantly improves the accuracy of category-level retrieval methods. Our strategy outperforms all competing methods for retrieving or classifying images at a finer granularity than that available at train time. It also improves the accuracy for transfer learning tasks to fine-grained datasets, thereby establishing the new state of the art on five public benchmarks, like iNaturalist-2018.","url_abs":"https://arxiv.org/abs/2011.12982v1","url_pdf":"https://arxiv.org/pdf/2011.12982v1.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":"image-classification","task_name":"Image Classification"},{"task_slug":"learning-with-coarse-labels","task_name":"Learning with coarse labels"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-food-101","task":"Fine-Grained Image Classification","dataset":"Food-101","model":"Grafit (RegNet-8GF)","rank_in_archive_order":6,"of":15,"metrics":{"Accuracy":"93.7"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford","task":"Fine-Grained Image Classification","dataset":"Oxford 102 Flowers","model":"Grafit (RegNet-8GF)","rank_in_archive_order":7,"of":25,"metrics":{"Accuracy":"99.1%"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","task":"Fine-Grained Image Classification","dataset":"Stanford Cars","model":"Grafit (RegNet-8GF)","rank_in_archive_order":36,"of":83,"metrics":{"Accuracy":"94.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"Grafit (ResNet-50)","rank_in_archive_order":84,"of":211,"metrics":{"Percentage correct":"83.7"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-flowers-102","task":"Image Classification","dataset":"Flowers-102","model":"Grafit (RegNet-8GF)","rank_in_archive_order":15,"of":52,"metrics":{"Accuracy":"99.1%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"Grafit (ResNet-50)","rank_in_archive_order":747,"of":1060,"metrics":{"Top 1 Accuracy":"79.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"RegNet-8GF","rank_in_archive_order":13,"of":60,"metrics":{"Top-1 Accuracy":"81.2%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"ResNet-50","rank_in_archive_order":39,"of":60,"metrics":{"Top-1 Accuracy":"69.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2019","task":"Image Classification","dataset":"iNaturalist 2019","model":"Grafit (RegnetY 8GF)","rank_in_archive_order":3,"of":22,"metrics":{"Top-1 Accuracy":"84.1"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-coarse-labels-on-imagenet32","task":"Learning with coarse labels","dataset":"ImageNet32","model":"Grafit","rank_in_archive_order":2,"of":2,"metrics":{"Recall@1":"18.13","Recall@10":"46.64","Recall@2":"25.46 ","Recall@5":"37.19 "},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-coarse-labels-on-stanford-cars","task":"Learning with coarse labels","dataset":"Stanford Cars","model":"Grafit","rank_in_archive_order":2,"of":2,"metrics":{"Recall@1":"42.30","Recall@10":"81.74","Recall@2":"54.79 ","Recall@5":"71.1 "},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-coarse-labels-on-stanford","task":"Learning with coarse labels","dataset":"Stanford Online Products","model":"Grafit","rank_in_archive_order":2,"of":2,"metrics":{"Recall@1":"74.02","Recall@10":"87.91","Recall@2":"78.82 ","Recall@5":"84.13"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-coarse-labels-on-cifar100","task":"Learning with coarse labels","dataset":"cifar100","model":"Grafit","rank_in_archive_order":2,"of":2,"metrics":{"Recall@1":"60.57","Recall@10":"89.21","Recall@2":"71.13","Recall@5":"82.32"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.12982","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}