Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation

We propose a novel model named Multi-Channel Attention Selection Generative Adversarial Network (SelectionGAN) for guided image-to-image translation, where we translate an input image into another while respecting an external semantic guidance. The proposed SelectionGAN explicitly utilizes the seman...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2023-05, Vol.45 (5), p.1-16
Main Authors: Tang, Hao, Torr, Philip H.S., Sebe, Nicu
Format: Article
Language:English
Subjects:
Cascade generation
deep attention selection
GANs
Generative adversarial networks
guided image-to-image translation
Image segmentation
Image synthesis
Modules
Network management systems
Optimization
Semantics
Skeleton
Task analysis
Uncertainty
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a novel model named Multi-Channel Attention Selection Generative Adversarial Network (SelectionGAN) for guided image-to-image translation, where we translate an input image into another while respecting an external semantic guidance. The proposed SelectionGAN explicitly utilizes the semantic guidance information and consists of two stages. In the first stage, the input image and the conditional semantic guidance are fed into a cycled semantic-guided generation network to produce initial coarse results. In the second stage, we refine the initial results by using the proposed multi-scale spatial pooling & channel selection module and the multi-channel attention selection module. Moreover, uncertainty maps automatically learned from attention maps are used to guide the pixel loss for better network optimization. Exhaustive experiments on four challenging guided image-to-image translation tasks (face, hand, body, and street view) demonstrate that our SelectionGAN is able to generate significantly better results than the state-of-the-art methods. Meanwhile, the proposed framework and modules are unified solutions and can be applied to solve other generation tasks such as semantic image synthesis. The code is available at  https://github.com/Ha0Tang/SelectionGAN .
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2022.3212915