PyTorch implementation of 2D sliding window attention
😎 An up-to-date & curated list of awesome semi-supervised learning papers, methods & resources.
A high-level toolbox for using complex valued neural networks in PyTorch
CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.
A PyTorch toolbox for domain adaptation and semi-supervised learning.
Implementation of Some Deep Hash Algorithms, Including DPSH、DSH、DHN、HashNet、DSDH、DTSH、DFH、GreedyHash、CSQ.
DSMIL: Multiple instance learning networks for tumor detection in Whole Slide Image
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
Pytorch implementation of our paper "Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling"
Histogram layer code for "Histogram Layers for Texture Analysis" (https://arxiv.org/abs/2001.00215).
Repository for the CVPR19 oral paper "Domain Generalization by Solving Jigsaw Puzzles"
Pytorch implementation of various Knowledge Distillation (KD) methods.
Image Retrieval by Hierarchy-aware Deep Hashing Based on Multi-task Learning
Transfer learning for iris segmentation and localization in NIR-ISL 2021
Code for the CVPR2021 paper "Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition"
precise iris segmentation
Codebase for Image Classification Research, written in PyTorch.
[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.
[Active development]ToolBox to make using Pytorch much easier.Give it a star if you feel helpful.
A PyTorch-based library for semi-supervised learning (NeurIPS'21)
This is an official implementation for "Self-Supervised Learning with Swin Transformers".
official implementation of UniFormer
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
VOLO: Vision Outlooker for Visual Recognition