Multi-Domain Image-to-Image Translation with Adaptive Inference Graph

TL;DR

This paper introduces an adaptive graph-based approach for multi-domain image-to-image translation that dynamically adjusts network capacity during inference, achieving high-quality results with limited computational resources.

Contribution

It proposes a novel adaptive graph structure that estimates sub-networks at inference time, reducing artifacts and computational costs in multi-domain translation.

Findings

Better image quality with fewer artifacts

Maintains constant computational cost

Effective on facial and painting datasets

Abstract

In this work, we address the problem of multi-domain image-to-image translation with particular attention paid to computational cost. In particular, current state of the art models require a large and deep model in order to handle the visual diversity of multiple domains. In a context of limited computational resources, increasing the network size may not be possible. Therefore, we propose to increase the network capacity by using an adaptive graph structure. At inference time, the network estimates its own graph by selecting specific sub-networks. Sub-network selection is implemented using Gumbel-Softmax in order to allow end-to-end training. This approach leads to an adjustable increase in number of parameters while preserving an almost constant computational cost. Our evaluation on two publicly available datasets of facial and painting images shows that our adaptive strategy generates better images with fewer artifacts than literature methods