SenseTime X-Lab

[ICCV 2023] DETRs with Collaborative Hybrid Assignments Training

[ICLR2022] official implementation of UniFormer

MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning

1st place models in Google OpenImage Detection Challenge 2019

A general video understanding codebase from SenseTime X-Lab

Unifying Visual Perception by Dispersible Points Learning (ECCV 2022)

[ICCV 2023] GeoMIM: towards better 3d knowledge transfer via masked image modeling for multi-view 3d understanding

[ICCV 2023] Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction

TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers (ECCV 2022)

Unified Architecture Search with Convolution, Transformer, and MLP (ECCV 2022)

Large-batch Optimization for Dense Visual Predictions (NeurIPS 2022)

Official implementation of "Self-slimmed Vision Transformer" (ECCV2022)

PPO x Family DRL Tutorial Course（决策智能入门级公开课：8节课帮你盘清算法理论，理顺代码逻辑，玩转决策AI应用实践 ）

OpenDILab Multi-Agent Environment