# Attention Mechanism for Contrastive Learning in GAN-based Image-to-Image Translation

## TL;DR

This paper introduces a GAN-based model enhanced with an attention mechanism and contrastive learning to generate high-quality, domain-adaptive images for autonomous driving, reducing reliance on real-world testing.

## Contribution

It combines attention mechanisms with contrastive learning in a GAN framework to improve image translation between virtual and real domains for autonomous driving.

## Key findings

- Generated images improve downstream task performance.
- Attention mechanism emphasizes significant source features.
- Model bridges the gap between virtual and real-world data.

## Abstract

Using real road testing to optimize autonomous driving algorithms is time-consuming and capital-intensive. To solve this problem, we propose a GAN-based model that is capable of generating high-quality images across different domains. We further leverage Contrastive Learning to train the model in a self-supervised way using image data acquired in the real world using real sensors and simulated images from 3D games. In this paper, we also apply an Attention Mechanism module to emphasize features that contain more information about the source domain according to their measurement of significance. Finally, the generated images are used as datasets to train neural networks to perform a variety of downstream tasks to verify that the approach can fill in the gaps between the virtual and real worlds.