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.
1 stories, newest first · one card per story
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.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views