Stars
[ICML'24] Open-Vocabulary Calibration for Fine-tuned CLIP
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
OpenMMLab Foundational Library for Training Deep Learning Models
A free and strong UCI chess engine
Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"
Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models. ECCV 2024
Self-supervised Augmentation Consistency for Adapting Semantic Segmentation (CVPR 2021)
Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video”
[CVPR'24] "Unsupervised Occupancy Learning from Sparse Point Cloud"
[ECCV'22] "Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Space"
Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation (CVPR-2024)
RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)
Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
Official pytorch implementation of BiMem: Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memory (ICCV 23)
Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024
PyTorch code and models for the DINOv2 self-supervised learning method.
Label Refinery: Improving ImageNet Classification through Label Progression
Multi-level Online Sequential Experts (MOSE) for online continual learning problem. (CVPR2024)
This is the official code implementation for 'What, How, and When Should Object Detectors Update in Continually Changing Test Domains?' presented at CVPR 2024.
[CVPR 2024] Domain Gap Embeddings for Generative Dataset Augmentation
BRAVO Challenge Toolkit and Evaluation Code
[WAVC 2024] Official implementation of the paper: Semantic Generative Augmentations for Few-shot Counting
Official PyTorch Implementation for "DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut", NeurIPS 2024
[ECML PKDD 24] The Simpler The Better: An Entropy-Based Importance Metric To Reduce Neural Networks’ Depth