Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Recent Transformer-based CV and related works.

A collection of resources on applications of Transformers in Medical Imaging.

[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI

Official PyTorch implementation of Fully Attentional Networks

EsViT: Efficient self-supervised Vision Transformers

Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".

🤗🖼️ HuggingPics: Fine-tune Vision Transformers for anything using images found on the web.

[NIVT Workshop @ ICCV 2023] SeMask: Semantically Masked Transformers for Semantic Segmentation

SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (ICCV 2023)

Implementation of MetNet-3, SOTA neural weather model out of Google Deepmind, in Pytorch

Implementation of CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

[ECCV 2022] The official repo for the paper "Poseur: Direct Human Pose Regression with Transformers".

Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.

A Monocular depth-estimation for in-the-wild AutoFocus application.

An unofficial implementation of ViTPose [Y. Xu et al., 2022]

Official repository for "Self-Supervised Video Transformer" (CVPR'22)

Few-Shot Diffusion Models