{"id":138418,"date":"2022-04-22T01:02:51","date_gmt":"2022-04-22T06:02:51","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2022\/04\/scientists-create-algorithm-to-assign-a-label-to-every-pixel-in-the-world-without-human-supervision"},"modified":"2022-04-22T01:02:51","modified_gmt":"2022-04-22T06:02:51","slug":"scientists-create-algorithm-to-assign-a-label-to-every-pixel-in-the-world-without-human-supervision","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2022\/04\/scientists-create-algorithm-to-assign-a-label-to-every-pixel-in-the-world-without-human-supervision","title":{"rendered":"Scientists create algorithm to assign a label to every pixel in the world, without human supervision"},"content":{"rendered":"<p><\/p>\n<p><iframe style=\"display: block; margin: 0 auto; width: 100%; aspect-ratio: 4\/3; object-fit: contain;\" src=\"https:\/\/www.youtube.com\/embed\/58uhMDO7dTQ?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope;\n   picture-in-picture\" allowfullscreen><\/iframe><\/p>\n<p>Labeling data can be a chore. It\u2019s the main source of sustenance for computer-vision models; without it, they\u2019d have a lot of difficulty identifying objects, people, and other important image characteristics. Yet producing just an hour of tagged and labeled data can take a whopping 800 hours of human time. Our high-fidelity understanding of the world develops as machines can better perceive and interact with our surroundings. But they need more help.<\/p>\n<p>Scientists from MIT\u2019s Computer Science and Artificial Intelligence Laboratory (CSAIL), Microsoft, and Cornell University have attempted to solve this problem plaguing vision models by creating \u201cSTEGO,\u201d an <a href=\"https:\/\/techxplore.com\/tags\/algorithm\/\" rel=\"tag\" class=\"\">algorithm<\/a> that can jointly discover and segment objects without any human labels at all, down to the pixel.<\/p>\n<p>STEGO learns something called \u201csemantic segmentation\u201d\u2014fancy speak for the process of assigning a label to every pixel in an image. Semantic segmentation is an important skill for today\u2019s computer-vision systems because images can be cluttered with objects. Even more challenging is that these objects don\u2019t always fit into literal boxes; algorithms tend to work better for discrete \u201cthings\u201d like people and cars as opposed to \u201cstuff\u201d like vegetation, sky, and mashed potatoes. A previous system might simply perceive a nuanced scene of a dog playing in the park as just a dog, but by assigning every pixel of the image a label, STEGO can break the image into its main ingredients: a dog, sky, grass, and its owner.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Labeling data can be a chore. It\u2019s the main source of sustenance for computer-vision models; without it, they\u2019d have a lot of difficulty identifying objects, people, and other important image characteristics. Yet producing just an hour of tagged and labeled data can take a whopping 800 hours of human time. Our high-fidelity understanding of the [\u2026]<\/p>\n","protected":false},"author":427,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[41,6,1491],"tags":[],"class_list":["post-138418","post","type-post","status-publish","format-standard","hentry","category-information-science","category-robotics-ai","category-transportation"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/138418","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/427"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=138418"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/138418\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=138418"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=138418"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=138418"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}