body { -ms-overflow-style: scrollbar; overflow-y: scroll; overscroll-behavior-y: none; } .errorContainer { background-color: #FFF; color: #0F1419; max-width: 600px; margin: 0 auto; padding: 10%; font-family: Helvetica, sans-serif; font-size: 16px; } .errorButton { margin: 3em 0; } .errorButton a { background: #1DA1F2; border-radius: 2.5em; color: white; padding: 1em 2em; text-decoration: none; } .errorButton a:hover, .errorButton a:focus { background: rgb(26, 145, 218); } .errorFooter { color: #657786; font-size: 80%; line-height: 1.5; padding: 1em 0; } .errorFooter a, .errorFooter a:visited { color: #657786; text-decoration: none; padding-right: 1em; } .errorFooter a:hover, .errorFooter a:active { text-decoration: underline; } #placeholder, #react-root { display: none !important; } body { background-color: #FFF !important; }

JavaScript is not available.

We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using twitter.com. You can see a list of supported browsers in our Help Center.

Help Center

Conversation

Vladimir Fomenko

@tvlfom

Excited to share that our work on "Learning to Discover and Detect Objects" got accepted to #neurips2022! 🌐: vlfom.github.io/RNCDL/ 📝: arxiv.org/abs/2210.10774 💻: github.com/vlfom/RNCDL

@Ismail_Elezi

Deva Ramanan

@lealtaixe

@AljosaOsep

5:25 AM · Oct 20, 2022

Replying to

We propose a two-phase object detection framework that uses constrained clustering and self-supervision on top of object proposals to localize novel classes in the wild. Our method beats SOTA when discovering 1000+ classes from LVIS using supervision for 80 COCO classes.