Search papers, labs, and topics across Lattice.
Affiliation:
3
0
4
3
A novel training strategy allows video segmentation models to learn from hours-long sequences, overcoming memory and gradient limitations to achieve 10x speedup over SOTA.
Get 3x faster image segmentation and comparable video segmentation performance to fine-tuned models, all while keeping your vision encoder frozen.
Ditch the complex trackers: a plain ViT encoder, augmented with a clever query propagation trick, delivers state-of-the-art video segmentation at 10x the speed.
