Logo image
A Co-Attention Method Based on Generative Adversarial Networks for Multi-view Images
Conference paper

A Co-Attention Method Based on Generative Adversarial Networks for Multi-view Images

Qi-Xian Huang, Shu-Pei Shi, Guo-Shiang Lin, Day-Fann Shen and Hung-Min Sun
Proceedings - 22nd IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2021-Fall, pp.171-173
2021

Abstract

co-attention map Deep Convolutional Generative Adversarial Networks Multi-view clothing Artificial Intelligence Computer Networks and Communications Computer Vision and Pattern Recognition Hardware and Architecture Software Information Systems and Management
In this paper, we use Deep Convolutional Generative Adversarial Networks (DCGANs) method to generate more images with multiple views to increase our dataset diversity. We use 3D-model different views for training DCGAN to make interpolation between the leftest and rightest random vectors, which means it can generate leftest to rightest images. After producing many of multi-view images, we combine with CNN based modules called co-attention map generator to look for common features of the same class but in different views clothing. By applying the learned generator to all images, the corresponding co-attention maps are obtained. we can fluently apply the proposed method can function well for multi-view objects on different types of clothing classes.

Metrics

1 Record Views

Details

Logo image