{"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/improving-image-recognition-by-retrieving","title":"Improving Image Recognition by Retrieving from Web-Scale Image-Text Data","arxiv_id":"2304.05173","date":"2023-04-11","proceeding":"CVPR 2023 1","authors":["Ahmet Iscen","Alireza Fathi","Cordelia Schmid"],"abstract":"Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar examples for the visual input from an external memory set. In this work, we introduce an attention-based memory module, which learns the importance of each retrieved example from the memory. Compared to existing approaches, our method removes the influence of the irrelevant retrieved examples, and retains those that are beneficial to the input query. We also thoroughly study various ways of constructing the memory dataset. Our experiments show the benefit of using a massive-scale memory dataset of 1B image-text pairs, and demonstrate the performance of different memory representations. We evaluate our method in three different classification tasks, namely long-tailed recognition, learning with noisy labels, and fine-grained classification, and show that it achieves state-of-the-art accuracies in ImageNet-LT, Places-LT and Webvision datasets.","url_abs":"https://arxiv.org/abs/2304.05173v1","url_pdf":"https://arxiv.org/pdf/2304.05173v1.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":"image-classification","task_name":"Image Classification"},{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-webvision-1000","task":"Image Classification","dataset":"WebVision-1000","model":"MAM (ViT-B/16)","rank_in_archive_order":1,"of":16,"metrics":{"Top-1 Accuracy":"83.6"},"uses_additional_data":true},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"MAM (ViT-B/16)","rank_in_archive_order":3,"of":69,"metrics":{"Top-1 Accuracy":"82.3"},"uses_additional_data":true},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"MAM (ViT-B/16)","rank_in_archive_order":3,"of":29,"metrics":{"Top-1 Accuracy":"51.4"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.05173","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}