Name: Weijian Deng
Type: User
Company: Australian National University
Bio: PhD in Machine Learning | Research Fellow@ANU | Predicting Model Generalization | 3D content Modeling & Generation | Build a Machine That Can See and Generalize
Location: Canberra
Blog: http://weijiandeng.xyz
Weijian Deng's Projects
[ICML'21] Estimate the accuracy of the classifier in various environments through self-supervision
CVPR and NeurIPS poster examples and templates. May we have in-person poster session soon!
repository for Universal Domain Adaptation through Self-supervision
Code accompanying the paper on "An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers" published at NeurIPS, 2021
We extend the SPGAN (our prior work in CVPR2018) to an end-to-end version, named eSPGAN. https://arxiv.org/pdf/1811.10551.pdf
2019 AI City Challenge in CVPR'19, Track 2, 3rd place
SPGAN in CVPR'18
Automatic model evaluation (AutoEval) in CVPR'21&TPAMI'22
PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).
Pytorch implement of Person re-identification baseline. We arrived Rank@1=88.24%, mAP=70.68% only with softmax loss. Re-ranking is added.
Code for https://arxiv.org/abs/1703.05693
VisDA2020: 4th Visual Domain Adaptation Challenge in ECCV'20
The code from the top teams in the VisDA-2020 Challenge in ECCV'20