GabrielXia

dino

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

Chinese-BERT-wwm

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

VIE

Codes for "Unsupervised Learning from Video with Deep Neural Embeddings"

meshed-memory-transformer

Meshed-Memory Transformer for Image Captioning. CVPR 2020

DeepLearningExamples

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

hgr_v2t

Code accompanying the paper "Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning".

byteps

A high performance and generic framework for distributed DNN training

Video-Description-via-Dialog-Agents-ECCV2020

[ECCV2020] Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents

FINCH-Clustering

Source Code for FINCH Clustering Algorithm

euler

A distributed graph deep learning framework.

LINE

LINE: Large-scale information network embedding

GraphEmbedding

Implementation and experiments of graph embedding algorithms.

simclr

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

fair_self_supervision_benchmark

Scaling and Benchmarking Self-Supervised Visual Representation Learning

LightGBM

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

PyClick

SCAN

PyTorch source code for "Stacked Cross Attention for Image-Text Matching" (ECCV 2018)

detr

End-to-End Object Detection with Transformers

TubeTK

Official implementation of paper: TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model (CVPR 2020 oral)

PyContrast

PyTorch implementation of Contrastive Learning methods

VSRN

PyTorch code for ICCV'19 paper "Visual Semantic Reasoning for Image-Text Matching"

vsepp

PyTorch Code for the paper "VSE++: Improving Visual-Semantic Embeddings with Hard Negatives"

TERN

Code and Resources for the Transformer Encoder Reasoning Network (TERN) - https://arxiv.org/abs/2004.09144

Ranked-List-Loss-for-DML

CVPR 2019: Ranked List Loss for Deep Metric Learning, with extension for TPAMI submission

decord

An efficient video loader for deep learning with smart shuffling that's super easy to digest

DTC

"Learning to Discover Novel Visual Categories via Deep Transfer Clustering" by Kai Han, Andrea Vedaldi, Andrew Zisserman (ICCV 2019)

remixmatch

fastText

Library for fast text representation and classification.

visualbert

Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"

tfrecord

TFRecord reader for PyTorch