LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors

arXiv:2403.14625v1 Announce Type: new
Abstract: We present a simple self-supervised method to enhance the performance of ViT features for dense downstream tasks. Our Lightweight Feature Transform (LiFT) is a straightforward and compact postprocessing network that can be applied to enhance the features of any pre-trained ViT backbone. LiFT is fast and easy to train with a self-supervised objective, and it boosts the density of ViT features for minimal extra inference cost. Furthermore, we demonstrate that LiFT can be applied with …

arxiv cs.cv feature simple type vit