DINOv2, every mention
1 scene · ← back to DINOv2
tap a year for its mentions
every year anyone Peter Robicheaux 7
Verbatim, from the transcripts: the passages where DINOv2 comes up
Best of 2024 in Vision [LS Live @ NeurIPS]
- ▶ 23:13 Peter Robicheaux So Dynav-II is a foundation model that was trained, um, self-supervised, purely on image data, um, and it kind of uses, like, some complex student-teacher framework, but essentially, and, like, it patches out, like, certain 7 times in the scene