Sen Pei's repositories
OPPO_6G_Data_Generation
Rank 3 : Source code for OPPO 6G Data Generation Challenge
Robust-Classification
CVPR 2022 Workshop Robust Classification
IncrementalVHD_GPE
official code for paper: Exploring Domain Incremental Video Highlights Detection with the LiveFood Benchmark
huawei_csig_action_recognition
Solution of team DS for HUAWEI CSIG action recognition challenge
Translation-Model
Transformer based language model.
3D-Box-Segment-Anything
We extend Segment Anything to 3D perception by combining it with VoxelNeXt.
adversarial-attacks-pytorch
PyTorch implementation of adversarial attacks.
ASL
Official Pytorch Implementation of: "Asymmetric Loss For Multi-Label Classification"(ICCV, 2021) paper
awesome-github-profile-readme
😎 A curated list of awesome GitHub Profile READMEs 📝
Awesome-Incremental-Learning
Awesome Incremental Learning
awesome-readme
A curated list of awesome READMEs
Best-README-Template
An awesome README template to jumpstart your projects!
detr
End-to-End Object Detection with Transformers
FAST-LIVO
A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry.
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.
github-readme-stats
:zap: Dynamically generated stats for your github readmes
mmdetection
OpenMMLab Detection Toolbox and Benchmark
ORBIT-Dataset
The ORBIT dataset is a collection of videos of objects in clean and cluttered scenes recorded by people who are blind/low-vision on a mobile phone. The dataset is presented with a teachable object recognition benchmark task which aims to drive few-shot learning on challenging real-world data.
robustbench
RobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]
standard-readme
A standard style for README files
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
VisualGPT
VisualGPT, CVPR 2022 Proceeding, GPT as a decoder for vision-language models