Computer Vision


Active Image Indexing

We reduce the quantization loss of a given image representation by making imperceptible changes to the image before its release. The loss is back-propagated through the deep...


The Casual Conversations v2 Dataset

This paper introduces a new large consent-driven dataset aimed at assisting in the evaluation of algorithmic bias and robustness of computer vision and audio speech models in...


Token Merging: Your ViT but faster

Meta AI is sharing new research to reduce the latency of existing Vision Transformer (ViT) models without the need for additional training. Our approach, called Token Merging...