AttentionGAN: Unpaired Image-to-Image Translation
A new Attention-Guided Generative Adversarial Network (AttentionGAN) for the unpaired image to image translation task.
Main Characteristic
AttentionGAN can identify the most discriminative foreground objects and minimize the change of the background. The attention-guided generators in AttentionGAN are able to produce attention masks, and then fuse the generation output with the attention masks to obtain high-quality target images.
Research areas
Integrative AI
Last updated
26.01.2024 - 10:21