(opens in new tab)<\/span><\/a>, which evaluates algorithms for object detection and image classification. The system also has top-notch accuracy, ranking second in detection and third in classification in the competition.<\/p>\nClearly, the SPP research has demonstrated the sort of progress that warrants further exploration.<\/p>\n
\u201cThough the current deep-learning models are breakthroughs over traditional methods, they are far from human performance, typically for the challenging detection task,\u201d He says. \u201cWe will continuously improve the quality of our methods.\u201d<\/p>\n
The ability to access ever-larger data sets will help advance the research.<\/p>\n
\u201cOne of the important next steps,\u201d Sun says, \u201cis to obtain much larger and richer training data. That will significantly impact the research in this direction.\u201d<\/p>\n
That said, it\u2019s hard for He to disguise his pride in what he and his colleagues have achieved.<\/p>\n
\u201cOur work is the fastest deep-learning system for accurate object detection,\u201d he says. \u201cThe speed is getting very close to the requirement for consumer usage.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"
In recent months, we\u2019ve heard a lot about deep neural networks and deep learning\u2014take Project Adam, for example\u2014and the sometimes eye-popping results they can have in addressing longstanding computing problems. The field of image recognition also is benefiting rapidly from the use of such networks, along with the availability of prodigious data sets. In this […]<\/p>\n","protected":false},"author":39507,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"categories":[194471,194480,194485],"tags":[195155,210674,186925,201273,187011,208719,210683,210677,210680],"research-area":[13561,13562,13551,13547],"msr-region":[197903],"msr-event-type":[],"msr-locale":[268875],"msr-post-option":[],"msr-impact-theme":[],"msr-promo-type":[],"msr-podcast-series":[],"class_list":["post-282233","post","type-post","status-publish","format-standard","hentry","category-computer-vision","category-graphics-and-multimedia","category-networking","tag-computing-in-the-21st-century-conference","tag-deep-convolutional-neural-networks-cnns","tag-deep-learning","tag-deep-neural-networks","tag-image-classification","tag-image-recognition","tag-imagenet-large-scale-visual-recognition-challenge-2014","tag-object-detection","tag-spatial-pyramid-pooling-spp","msr-research-area-algorithms","msr-research-area-computer-vision","msr-research-area-graphics-and-multimedia","msr-research-area-systems-and-networking","msr-region-asia-pacific","msr-locale-en_us"],"msr_event_details":{"start":"","end":"","location":""},"podcast_url":"","podcast_episode":"","msr_research_lab":[199560],"msr_impact_theme":[],"related-publications":[],"related-downloads":[],"related-videos":[],"related-academic-programs":[],"related-groups":[],"related-projects":[],"related-events":[],"related-researchers":[],"msr_type":"Post","byline":"","formattedDate":"October 28, 2014","formattedExcerpt":"In recent months, we\u2019ve heard a lot about deep neural networks and deep learning\u2014take Project Adam, for example\u2014and the sometimes eye-popping results they can have in addressing longstanding computing problems. The field of image recognition also is benefiting rapidly from the use of such networks,…","locale":{"slug":"en_us","name":"English","native":"","english":"English"},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/282233"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/users\/39507"}],"replies":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/comments?post=282233"}],"version-history":[{"count":7,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/282233\/revisions"}],"predecessor-version":[{"id":282854,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/282233\/revisions\/282854"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=282233"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/categories?post=282233"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/tags?post=282233"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=282233"},{"taxonomy":"msr-region","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-region?post=282233"},{"taxonomy":"msr-event-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event-type?post=282233"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=282233"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=282233"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=282233"},{"taxonomy":"msr-promo-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-promo-type?post=282233"},{"taxonomy":"msr-podcast-series","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-podcast-series?post=282233"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}