Implementation of Non-local Block.
Code release for "Adversarial Robustness vs Model Compression, or Both?"
Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"
An out-of-box human parsing representation extractor. This is also the CVPR2019 3rd LIP challenge winner solution!
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCVW 2019 https://arxiv.org/abs/1901.00212
Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
Official code for the paper "InGAN: Capturing and Retargeting the DNA of a Natural Image"
A collection of AWESOME things about domian adaptation
Pytorch implementations of referring expression networks
Referring Expression Object Segmentation with Caption-Aware Consistency, BMVC 2019
higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
books, projects and memos
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations, CVPR 2019 (Oral)
PyTorch Meta-learning Framework for Researchers
[COLING 2018] Learning Visually-Grounded Semantics from Contrastive Adversarial Samples.
Unsupervised Domain Adaptation Papers and Code
A tiny, friendly, strong pytorch implement of person re-identification baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
Generative Tensorial Reinforcement Learning (GENTRL) model
This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned"
Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
🦓<->🦒 🌃<->🌆 A collection of image to image papers with code (constantly updating)
[ICCV 2019] AutoGAN: Neural Architecture Search for Generative Adversarial Networks
CVPR2019 Joint Discriminative and Generative Learning for Person Re-identification
Temporal Relation Networks
links to conference publications in graph-based deep learning
Reference models and tools for Cloud TPUs.
Self-supervised Representation Learning from Videos for Facial Action Unit Detection