Junru Wu's repositories
WeakNAS-1
[NeurIPS 2021] “Stronger NAS with Weaker Predictors“, Junru Wu, Xiyang Dai, Dongdong Chen, Yinpeng Chen, Mengchen Liu, Ye Yu, Zhangyang Wang, Zicheng Liu, Mei Chen and Lu Yuan
siren
Official implementation of "Implicit Neural Representations with Periodic Activation Functions"
ClassyVision
An end-to-end PyTorch framework for image and video classification
vision
Datasets, Transforms and Models specific to Computer Vision
CVPR2019-MADDoG
Codes for Multi-adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection
typo
Typo is the oldest and most powerful Ruby on Rails blogware, providing custom templates, powerful drag and drop plugins API, advanced SEO capabilities, XMLRPC API and many more.
rottenpotatoes-rails-intro
RottenPotatoes app skeleton for saasbook/hw-rails-intro
hw-ruby-intro
Ruby Introduction Assignment for Agile Development using Ruby on Rails
UAV-NDFT
[ICCV 2019] "Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach"
USAID
[Preprint] "Segmentation-Aware Image Denoising without Knowing True Segmentation"
ABD-Net
[ICCV 2019] "ABD-Net: Attentive but Diverse Person Re-Identification" https://arxiv.org/abs/1908.01114
EnlightenGAN
EnlightenGAN: Deep Light Enhancement without Paired Supervision
stuff
Stuff I uploaded to share online or to access from a different machine
TimeCycle
Learning Correspondence from the Cycle-consistency of Time (CVPR 2019)
996.ICU
Repo for counting stars and contributing. Press F to pay respect to glorious developers.
ultra_high_resolution_segmentation
code used for CVPR2019 oral "Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images"
video-nonlocal-net
Non-local Neural Networks for Video Classification
autokeras
accessible AutoML for deep learning.
Semantic_Human_Matting
Semantic Human Matting
Can-we-Gain-More-from-Orthogonality
Official Implementation for https://arxiv.org/abs/1810.09102
vid2vid
Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.