Mask Based Unsupervised Content Transfer

06/15/2019
by   Ron Mokady, et al.
3

We consider the problem of translating, in an unsupervised manner, between two domains where one contains some additional information compared to the other. The proposed method disentangles the common and separate parts of these domains and, through the generation of a mask, focuses the attention of the underlying network to the desired augmentation alone, without wastefully reconstructing the entire target. This enables state-of-the-art quality and variety of content translation, as shown through extensive quantitative and qualitative evaluation. Furthermore, the novel mask-based formulation and regularization is accurate enough to achieve state-of-the-art performance in the realm of weakly supervised segmentation, where only class labels are given. To our knowledge, this is the first report that bridges the problems of domain disentanglement and weakly supervised segmentation. Our code is publicly available at https://github.com/rmokady/mbu-content-tansfer.

READ FULL TEXT

page 17

page 18

page 24

page 25

page 26

page 28

page 29

page 31

research
09/28/2020

Weakly Supervised Deep Functional Map for Shape Matching

A variety of deep functional maps have been proposed recently, from full...
research
10/25/2022

Pointly-Supervised Panoptic Segmentation

In this paper, we propose a new approach to applying point-level annotat...
research
11/06/2020

A Weakly Supervised Convolutional Network for Change Segmentation and Classification

Fully supervised change detection methods require difficult to procure p...
research
08/30/2019

Domain Intersection and Domain Difference

We present a method for recovering the shared content between two visual...
research
09/04/2019

Mixture Content Selection for Diverse Sequence Generation

Generating diverse sequences is important in many NLP applications such ...
research
11/04/2020

Crack Detection as a Weakly-Supervised Problem: Towards Achieving Less Annotation-Intensive Crack Detectors

Automatic crack detection is a critical task that has the potential to d...
research
07/19/2020

Geometry Constrained Weakly Supervised Object Localization

We propose a geometry constrained network, termed GC-Net, for weakly sup...

Please sign up or login with your details

Forgot password? Click here to reset