Home

Requirements Pillow tabulate Check PyTorch, CUDA, cuDNN Versions on Ubuntu and Windows # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved import numpy as np import os import subprocess import sys from collections import defaultdict import PIL import torch import torchvision from tabulate import tabulate __all__ = ["...

Info Title: Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation Task: Image-to-Image Translation Author: Arnab Ghosh Richard Zhang Puneet K. Dokania Oliver Wang Alexei A. Efros Philip H. S. Torr Eli Shechtman Date: Sep. 2019 Arxiv: 1909.11081 Published: ICCV 2019 Highlights Interactive GUI First complete,...

Info Title: Temporal Cycle-Consistency Learning Task: Representation Learning Author: Debidatta Dwibedi, Yusuf Aytar , Jonathan Tompson, Pierre Sermanet, and Andrew Zisserman Date: Apr. 2019 Arxiv: 1904.07846 Published: CVPR 2019 Highlights Temporal cycle-consistency (TCC) loss for video alignment in learned latent space with a ...

Info Title: Seeing What a GAN Cannot Generate Author: Date: Sep. 2019 Paper Published: ICCV 2019 Abstract Despite the success of Generative Adversarial Networks(GANs), mode collapse remains a serious issue during GAN training. To date, little work has focused on understanding and quantifying which modes have been dropped by a model...

Info Title: Unsupervised Domain Adaptation through Self-Supervision Task: Domain Adaptaion Author: Yu Sun, Eric Tzeng, Trevor Darrell, Alexei A. Efros Date: Sep. 2019 Arxiv: 1909.11825 Abstract This paper addresses unsupervised domain adaptation, the setting where labeled training data is available on a source domain, but the goal...

Info Title: Multi-mapping Image-to-Image Translation via Learning Disentanglement Task: Image Translation Author: Date: Sep. 2019 Arxiv: 1909.07877 Published: NIPS 2019 Highlights Multi-modal multi-domain translation with unified structure. Abstract Recent advances of image-to-image translation focus on learning the one-to-man...

Info Title: Test-Time Training for Out-of-Distribution Generalization Author: Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, Moritz Hardt Date: Sep. 2019 Arxiv: 1909.13231 Highlights Theoretically prove of benefits on test-time self-supervised training for convex loss functions, e...

Info Title: Learning Correspondence from the Cycle-Consistency of Time Task: Representation Learning Author: Xiaolong Wang, Allan Jabri, Alexei A. Efros Date: Mar. 2019 Arxiv: 1903.07593 Published: CVPR 2019 Highlights Self-supervised for representation learning inside single video The learned representation can be generali...