Attention-GAN for Object Transfiguration in Wild Images

Abstract

This paper studies the object transfiguration problem in wild images. The generative network in classical GANs for object transfiguration often undertakes a dual responsibility: to detect the objects of interests and to convert the object from source domain to target domain. In contrast, we decompose the generative network into two separat networks, each of which is only dedicated to one particular sub-task. The attention network predicts spatial attention maps of images, and the transformation network focuses on translating objects. Attention maps produced by attention network are encouraged to be sparse, so that major attention can be paid to objects of interests. No matter before or after object transfiguration, attention maps should remain constant. In addition, learning attention network can receive more instructions, given the available segmentation annotations of images. Experimental results demonstrate the necessity of investigating attention in object transfiguration, and that the proposed algorithm can learn accurate attention to improve quality of generated images.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• DRAW: A Recurrent Neural Network For Image Generation
• Unsupervised Cross-Domain Image Generation
• DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
• LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
• Describing Videos by Exploiting Temporal Structure
• Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
• One-Sided Unsupervised Domain Mapping
• Generating Images Part by Part with Composite Generative Adversarial Networks
• Scribbler: Controlling Deep Image Synthesis with Sketch and Color

Cited by in corpus (4)

• Region Based Adversarial Synthesis of Facial Action Units
• Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation
• Class Activation Map Generation by Representative Class Selection and Multi-Layer Feature Fusion
• Synthesizing Photorealistic Images with Deep Generative Learning