Repositories tagged with "vision-transformers"
pytorch-grad-cam
jacobgil
โAdvanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.โ
Transformer-in-Vision
DirtyHarryLYL
โRecent Transformer-based CV and related works.โ
awesome-transformers-in-medical-imaging
fahadshamshad
โA collection of resources on applications of Transformers in Medical Imaging.โ
PoinTr
yuxumin
โ[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformersโ
Uni3D
baaivision
โ[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAIโ
DynamicViT
raoyongming
โ[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationโ
FAN
NVlabs
โOfficial PyTorch implementation of Fully Attentional Networksโ
dino-vit-features
ShirAmir
โOfficial implementation for the paper "Deep ViT Features as Dense Visual Descriptors".โ
esvit
microsoft
โEsViT: Efficient self-supervised Vision Transformersโ
huggingpics
nateraw
โ๐ค๐ผ๏ธ HuggingPics: Fine-tune Vision Transformers for anything using images found on the web.โ
SimpleClick
uncbiag
โSimpleClick: Interactive Image Segmentation with Simple Vision Transformers (ICCV 2023)โ
SeMask-Segmentation
Picsart-AI-Research
โ[NIVT Workshop @ ICCV 2023] SeMask: Semantically Masked Transformers for Semantic Segmentationโ
metnet3-pytorch
lucidrains
โImplementation of MetNet-3, SOTA neural weather model out of Google Deepmind, in Pytorchโ
CrossViT-pytorch
rishikksh20
โImplementation of CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationโ
code-samples
all-things-vits
โHolds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.โ
Poseur
aim-uofa
โ[ECCV 2022] The official repo for the paper "Poseur: Direct Human Pose Regression with Transformers".โ
FocusOnDepth
antocad
โA Monocular depth-estimation for in-the-wild AutoFocus application.โ
ViTPose_pytorch
jaehyunnn
โAn unofficial implementation of ViTPose [Y. Xu et al., 2022] โ
