PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Code release for "HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs" at AAAI 2020.
Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners
OpenMMLab Detection Toolbox and Benchmark
NeRF visualization library under construction
Self-Supervised Learning Toolbox and Benchmark
Source code of Universal Weighting Metric Learning for Cross-Modal Matching. The paper is accepted by CVPR2020.
Position Focused Attention Network for Image-Text Matching
Official PyTorch Implementation of Proxy Anchor Loss for Deep Metric Learning, CVPR 2020
ResNeSt: Split-Attention Networks
PyTorch source code for "Stacked Cross Attention for Image-Text Matching" (ECCV 2018)
Setup a new machine without sudo!
A full-fledged version of Pix2Seq
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
My personal website.