1.0Salesforcehttps://www.salesforce.com/blogDonald Rosehttps://www.salesforce.com/blog/author/donald-rose/rich600338<blockquote class="wp-embedded-content" data-secret="LbWYK6ZC7y"><a href="https://www.salesforce.com/blog/pb-ovd-open-vocabulary-object-detector/">Open Vocabulary Object Detection with Pseudo Bounding-Box Labels: Towards a Universal Object Detector</a></blockquote><iframe sandbox="allow-scripts" security="restricted" src="https://www.salesforce.com/blog/pb-ovd-open-vocabulary-object-detector/embed/#?secret=LbWYK6ZC7y" width="600" height="338" title="“Open Vocabulary Object Detection with Pseudo Bounding-Box Labels: Towards a Universal Object Detector” — Salesforce" data-secret="LbWYK6ZC7y" frameborder="0" marginwidth="0" marginheight="0" scrolling="no" class="wp-embedded-content"></iframe><script> /*! This file is auto-generated */ !function(d,l){"use strict";l.querySelector&&d.addEventListener&&"undefined"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!/[^a-zA-Z0-9]/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret="'+t.secret+'"]'),o=l.querySelectorAll('blockquote[data-secret="'+t.secret+'"]'),c=new RegExp("^https?:$","i"),i=0;i<o.length;i++)o[i].style.display="none";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute("style"),"height"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):"link"===t.message&&(r=new URL(s.getAttribute("src")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener("message",d.wp.receiveEmbedMessage,!1),l.addEventListener("DOMContentLoaded",function(){for(var e,t,s=l.querySelectorAll("iframe.wp-embedded-content"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute("data-secret"))||(t=Math.random().toString(36).substring(2,12),e.src+="#?secret="+t,e.setAttribute("data-secret",t)),e.contentWindow.postMessage({message:"ready",secret:t},"*")},!1)))}(window,document); //# sourceURL=https://wp-bn.salesforce.com/blog/wp-includes/js/wp-embed.min.js </script> Most AI object-detection methods work only on limited object categories, due to the human effort needed to create bounding-box labels for training data. Our new method automatically generates pseudo bounding-box labels of diverse objects from large-scale image-caption pairs, and we found it outperforms the SOTA open vocabulary object detector. Its AI-generated bounding-box labels and strong generalization performance on novel datasets bring us closer to the dream of a universal object detector.https://lh6.googleusercontent.com/Azf5TXbU5CV1B228Wit9ndFC-u5RlTqwFAH34jg5w73pzIWSJ5MOpzkk4HvMIMJwvjGlGu77S1fzVnm4iDBKJcAR-4t66P2vxNza2FxpBa4SH37yJiUU0cZl_qNVJluqarr0v6F4YwrSgLzbbfnarZA