Avilasha Mandal

RS$^3$-Prune: Read-Sparse, Store-Sparse Token Pruning for Video Object Segmentation

We introduce RS$^3$-Prune, a training-free token-pruning recipe that instantiates as a small set of inference time hooks atop existing video object segmentation (VOS) networks. Modern VOS models have converged on a common, expensive design: an image encoder produces a dense token grid for every frame, and a memory bank...