{"id":214893,"date":"2025-05-27T17:20:36","date_gmt":"2025-05-27T22:20:36","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2025\/05\/self-trained-vision-transformers-mimic-human-gaze-with-surprising-precision"},"modified":"2025-05-27T17:20:36","modified_gmt":"2025-05-27T22:20:36","slug":"self-trained-vision-transformers-mimic-human-gaze-with-surprising-precision","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2025\/05\/self-trained-vision-transformers-mimic-human-gaze-with-surprising-precision","title":{"rendered":"Self-trained vision transformers mimic human gaze with surprising precision"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/self-trained-vision-transformers-mimic-human-gaze-with-surprising-precision2.jpg\"><\/a><\/p>\n<p>Can machines ever see the world as we see it? Researchers have uncovered compelling evidence that vision transformers (ViTs), a type of deep-learning model that specializes in image analysis, can spontaneously develop human-like visual attention patterns when trained without labeled instructions.<\/p>\n<p>Visual attention is the mechanism by which organisms, or <a href=\"https:\/\/techxplore.com\/tags\/artificial+intelligence\/\" rel=\"tag\" class=\"\">artificial intelligence<\/a> (AI), filter out \u201cvisual noise\u201d to focus on the most relevant parts of an image or view. While natural for humans, spontaneous learning has proven difficult for AI.<\/p>\n<p>However, researchers have revealed, in their recent <a href=\"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025004757\" target=\"_blank\">publication<\/a> in <i>Neural Networks<\/i>, that with the right training experience, AI can spontaneously acquire human-like visual attention without being explicitly taught to do so.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Can machines ever see the world as we see it? Researchers have uncovered compelling evidence that vision transformers (ViTs), a type of deep-learning model that specializes in image analysis, can spontaneously develop human-like visual attention patterns when trained without labeled instructions. Visual attention is the mechanism by which organisms, or artificial intelligence (AI), filter out [\u2026]<\/p>\n","protected":false},"author":718,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-214893","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/214893","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\/718"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=214893"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/214893\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=214893"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=214893"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=214893"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}