{"id":385382,"date":"2017-05-21T18:43:15","date_gmt":"2017-05-22T01:43:15","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=385382"},"modified":"2021-05-11T21:08:00","modified_gmt":"2021-05-12T04:08:00","slug":"fine-grained-image-recognition","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/fine-grained-image-recognition\/","title":{"rendered":"Fine-grained Image Recognition"},"content":{"rendered":"<p>Recognizing fine-grained categories (e.g., bird species) is difficult due to the challenges of discriminative region localization and fine-grained feature learning. In this project, we are aiming at recognizing the fine-grained image categories at a very high accuracy. For example, now we can recognize more 1,000 flower species, 200 birds, 200 dogs, 800+ car models with the accuracy higher than 88% in several large-scale real-world datasets.<\/p>\n<p>In our work accepted to CVPR 2017, we propose a novel recurrent attention convolutional neural network (RA-CNN) which recursively learns discriminative region attention and region-based feature representation at multiple scales in a mutually reinforced way. We also release Microsoft Flower Recognition (<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/project\/flowerreco-cn\/\">\u5fae\u8f6f\u8bc6\u82b1<\/a>App) as an iOS application.<\/p>\n<div id=\"attachment_385385\" style=\"width: 511px\" class=\"wp-caption alignnone\"><img loading=\"lazy\" decoding=\"async\" aria-describedby=\"caption-attachment-385385\" class=\" wp-image-385385\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2017\/05\/fine-grained-image-recog-1024x680.jpg\" alt=\"\" width=\"501\" height=\"328\" \/><p id=\"caption-attachment-385385\" class=\"wp-caption-text\">Figure: Fine-grained image recognition.<\/p><\/div>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-385388 alignnone\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2017\/05\/microsoft-flower-recognition-1024x431.jpg\" alt=\"\" width=\"670\" height=\"285\" \/><br \/>\nFigure: Microsoft Flower Recognition (&#8220;<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/project\/flowerreco-cn\/\">\u5fae\u8f6f\u8bc6\u82b1<\/a>&#8220;)<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Recognizing fine-grained categories (e.g., bird species) is difficult due to the challenges of discriminative region localization and fine-grained feature learning. In this project, we are aiming at recognizing the fine-grained image categories at a very high accuracy. For example, now we can recognize more 1,000 flower species, 200 birds, 200 dogs, 800+ car models with [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13562,13551],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-385382","msr-project","type-msr-project","status-publish","hentry","msr-research-area-computer-vision","msr-research-area-graphics-and-multimedia","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"2016-07-01","related-publications":[418061,431118],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Jianlong Fu","user_id":32260,"people_section":"Group 1","alias":"jianf"}],"msr_research_lab":[199560],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/385382"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/385382\/revisions"}],"predecessor-version":[{"id":745585,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/385382\/revisions\/745585"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=385382"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=385382"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=385382"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=385382"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=385382"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}