The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

This repository contains implementations and illustrative code to accompany DeepMind publications

PyTorch code and models for the DINOv2 self-supervised learning method.

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

[DEIMv2] Real Time Object Detection Meets DINOv3

[CVPR2026] Detect Anything via Next Point Prediction

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

iBOT 🤖: Image BERT Pre-Training with Online Tokenizer (ICLR 2022)

Official PyTorch implementation of "Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup" (ICML'20)

DEIMKit is a Python package that provides a wrapper for DEIM: DETR with Improved Matching for Fast Convergence. Check out the original repo for more details.

Code for the paper "A Light Recipe to Train Robust Vision Transformers" [SaTML 2023]

A simple wrapper library for binding timm models as detectron2 backbones