157 Open source projects that are alternatives of or similar to PASSL

A PaddlePaddle version image model zoo.

Paddle Large Scale Classification Tools，supports ArcFace, CosFace, PartialFC, Data Parallel + Model Parallel. Model includes ResNet, ViT, DeiT, FaceViT.

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

pix2tex: Using a ViT to convert images of equations into LaTeX code.

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

A PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer".

TransMorph: Transformer for Unsupervised Medical Image Registration (PyTorch)

LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations. [NeurIPS 2021]

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision

Exploring Simple Siamese Representation Learning

This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

Official PyTorch implementation of our ECCV 2022 paper "Sliced Recursive Transformer"

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

Official code for "Mean Shift for Self-Supervised Learning"

Oriented Object Detection: Oriented RepPoints + Swin Transformer/ReResNet

(ICCV 2021) BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search

Code to train the SimSiam model on cifar10 using PyTorch

[CVPR21] Implementation of our work "Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation"

Code for our ACML and INTERSPEECH papers: "Speaker Diarization as a Fully Online Bandit Learning Problem in MiniVox".

You Only Look at One Sequence (NeurIPS 2021)

List of Publications in Graph Contrastive Learning

This is the code base for paper "G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling" by Souradip Chakraborty, Aritra Roy Gosthipaty and Sayak Paul.

🎨 provide some common image process apis with canvas

A TensorFlow 2.x implementation of Masked Autoencoders Are Scalable Vision Learners

PyTorch implementation of our CVPR2021 (oral) paper "Prototype Augmentation and Self-Supervision for Incremental Learning"

A Fast Knowledge Distillation Framework for Visual Recognition

A containerized REST API around OpenAI's CLIP model.

(Minimally) implements SimCLR (https://arxiv.org/abs/2002.05709) in TensorFlow 2.

PySODEvalToolkit: A Python-based Evaluation Toolbox for Salient Object Detection and Camouflaged Object Detection

code for CVPR-2019 paper: Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics

Natural World Tasks

[WWW 2021] Source code for "Graph Contrastive Learning with Adaptive Augmentation"

[NeurIPS 2021 Spotlight] Aligning Pretraining for Detection via Object-Level Contrastive Learning

a collection of visualization function

一个简单的移动端裁剪图片上传插件

FisheyeDistanceNet

Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning

Self-Supervised Pillar Motion Learning for Autonomous Driving (CVPR 2021)

Pytorch Lightning Implementation of SC-Depth (V1, V2...) for Unsupervised Monocular Depth Estimation.

EsViT: Efficient self-supervised Vision Transformers

The code for our IEEE ACCESS (2020) paper Multimodal Emotion Recognition with Transformer-Based Self Supervised Feature Fusion.

Vision Transformer for 3D medical image registration (Pytorch).

Implementation of paper "Self-supervised Learning on Graphs:Deep Insights and New Directions"

Mobile(iOS) Text-to-Image search powered by multimodal semantic representation models(e.g., OpenAI's CLIP). Accepted at NAACL 2022.

Pytorch implementation of "A Simple Framework for Contrastive Learning of Visual Representations"

Variants of Vision Transformer and its downstream tasks

A curated list of awesome graph & self-supervised-learning-based recommendation.

KoCLIP: Korean port of OpenAI CLIP, in Flax

InterpretDL: Interpretation of Deep Learning Models，基于『飞桨』的模型可解释性算法库。

This repository contains demos I made with the Transformers library by HuggingFace.

PyTorch implementation of the InfoNCE loss for self-supervised learning.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.

Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer

AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries

code for AAAI21 paper "Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion“

低代码序列数据处理框架，最短两行即可完成训练任务！

Generalized Deep Metric Learning.

Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle.