PaceShift adds guarded curriculum training for dense prediction
The method keeps the deployed architecture unchanged and adds no inference computation; code is not yet public.
Stories per day · 30 days
2 RSS
2 stories, newest first · one card per story
Stories tagged #dense-prediction
GTR: Gated Token Recurrence for Efficient Dense Prediction
GTR introduces a softmax-free recurrent vision backbone reaching 58.9 box AP on COCO with sub-2ms latency, targeting high-resolution dense prediction and edge deployment.