Jackson Wang's Projects
Annealed Importance Sampling (AIS) for generative models.
Code for "Adversarial Distillation of Bayesian Neural Network Posteriors" https://arxiv.org/abs/1806.10317
PyTorch implementation of Bidirectional Monte Carlo, Annealed Importance Sampling, and Hamiltonian Monte Carlo
A drop-in replacement for CIFAR-10.
A library for benchmarking vulnerability to adversarial examples
source code to ICLR'19, 'A Closer Look at Few-shot Classification'
Differentiable Augmentation for Data-Efficient GAN Training
Fast k-Nearest Neighbour Search using Dynamic Continuous Indexing (DCI)
Motion Retargeting Video Subjects
Kuan-Chieh Wang, Paul Vicol, Eleni Triantafillou, Richard Zemel. (2020). “Few-shot Out-of-Distribution Detection.” (ICML) Workshop on Uncertainty and Robustness in Deep Learning
[CVPR 2022 Oral] Official PyTorch Implementation of "GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras”.
Simple, extendable, easy to understand Glow implementation in PyTorch
Distributionally robust neural networks for group shifts
Code for reproducing experiments in "Improved Training of Wasserstein GANs"
Code for the ICCV 2017 paper "Introspective Neural Networks for Generative Modeling"
Pytorch0.4.1 codes for InsightFace
The official PyTorch implementation of the paper "Human Motion Diffusion Model"
[CVPR 2023 Highlight] Official implementation of "NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action"
PyTorch Implementation of Neural Statistician
Pytorch implementations of density estimation algorithms: BNAF, Glow, MAF, RealNVP, planar flows
The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)
A Port of Fréchet Inception Distance (FID score) to PyTorch
Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)
Modified from the original tensorflow version.
Corruption and Perturbation Robustness (ICLR 2019)
work in progres.....
Good Semi-Supervised Learning That Requires a Bad GAN