Diffusion-TTA improves pre-trained discriminative models such as image classifiers or segmentors using pre-trained generative models.

Inference code for Llama models

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

Extended LaTeX template for CVPR/ICCV papers

Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022

Matplotlib style sheets to nicely format figures for scientific papers, thesis and presentations while keeping them fully editable in Adobe Illustrator.

Boundary IoU API (Beta version)

Code release for "COTR: Correspondence Transformer for Matching Across Images"(ICCV 2021)

A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning

QuadTree Attention for Vision Transformers (ICLR2022)

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Code, data and benchmark from the paper "Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming" (NeurIPS 2019 ML4AD)

[NeurIPS'21] Unified tracking framework with a single appearance model. It supports Single Object Tracking (SOT), Video Object Segmentation (VOS), Multi-Object Tracking (MOT), Multi-Object Tracking…

Test-Time Personalization with a Transformer for Human Pose Estimation, NeurIPS 2021

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

A Cataract Dataset for Tool Detection.

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

Dense matching library based on PyTorch

Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)

IS, FID score Pytorch and TF implementation, TF implementation is a wrapper of the official ones.

A library for efficient similarity search and clustering of dense vectors.

SOTA medical image segmentation methods based on various challenges

Transformer: PyTorch Implementation of "Attention Is All You Need"

PyTorch package for the discrete VAE used for DALL·E.

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

A PyTorch implementation of the 1d and 2d Sinusoidal positional encoding/embedding.

Source code for Neural Information Processing Systems (NeurIPS) 2018 paper "Multi-Task Learning as Multi-Objective Optimization"

A curated list of awesome computer vision resources

[NeurIPS 2020] Semi-Supervision (Unlabeled Data) & Self-Supervision Improve Class-Imbalanced / Long-Tailed Learning