A Semi-Paired Approach For Label-to-Image Translation

by   George Eskandar, et al.

Data efficiency, or the ability to generalize from a few labeled data, remains a major challenge in deep learning. Semi-supervised learning has thrived in traditional recognition tasks alleviating the need for large amounts of labeled data, yet it remains understudied in image-to-image translation (I2I) tasks. In this work, we introduce the first semi-supervised (semi-paired) framework for label-to-image translation, a challenging subtask of I2I which generates photorealistic images from semantic label maps. In the semi-paired setting, the model has access to a small set of paired data and a larger set of unpaired images and labels. Instead of using geometrical transformations as a pretext task like previous works, we leverage an input reconstruction task by exploiting the conditional discriminator on the paired data as a reverse generator. We propose a training algorithm for this shared network, and we present a rare classes sampling algorithm to focus on under-represented classes. Experiments on 3 standard benchmarks show that the proposed model outperforms state-of-the-art unsupervised and semi-supervised approaches, as well as some fully supervised approaches while using a much smaller number of paired samples.


Semi-Supervised Image-to-Image Translation using Latent Space Mapping

Recent image-to-image translation works have been transferred from super...

Towards Pragmatic Semantic Image Synthesis for Urban Scenes

The need for large amounts of training and validation data is a huge con...

Transformation Consistency Regularization- A Semi-Supervised Paradigm for Image-to-Image Translation

Scarcity of labeled data has motivated the development of semi-supervise...

USIS: Unsupervised Semantic Image Synthesis

Semantic Image Synthesis (SIS) is a subclass of image-to-image translati...

Semi-Supervised Graph-to-Graph Translation

Graph translation is very promising research direction and has a wide ra...

DS3-Net: Difficulty-perceived Common-to-T1ce Semi-Supervised Multimodal MRI Synthesis Network

Contrast-enhanced T1 (T1ce) is one of the most essential magnetic resona...

Please sign up or login with your details

Forgot password? Click here to reset