[NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

OVSegmentor, CVPR23

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

Official Implementation of Zero-guidance Segmentation (ICCV 2023)

Code for "TAG: Guidance-free Open-Vocabulary Semantic Segmentation"

Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.