Bi-GAE: A Bidirectional Generative Auto-Encoder

• Published in: Journal of computer science and technology Vol. 38; no. 3; pp. 626 - 643
• Main Authors: Hua, Qin, Hu, Han-Wen, Qian, Shi-You, Yang, Ding-Yu, Cao, Jian
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.06.2023; Springer; Springer Nature B.V
• Subjects: Analysis; Artificial Intelligence; Coders; Computer Science; Convergence; Data Structures and Information Theory; Decoding; Generative adversarial networks; Image resolution; Information Systems Applications (incl.Internet); Liquors; Mapping; Optimization; Regular Paper; Representations; Semantics; Software Engineering; Theory of Computation; image reconstruction and generation; auto-encoder; feature representation; adversarial network
• ISSN: 1000-9000; 1860-4749
• DOI: 10.1007/s11390-023-1902-1

Improving the generative and representational capabilities of auto-encoders is a hot research topic. However, it is a challenge to jointly and simultaneously optimize the bidirectional mapping between the encoder and the decoder/generator while ensuing convergence. Most existing auto-encoders cannot automatically trade off bidirectional mapping. In this work, we propose Bi-GAE, an unsupervised bidirectional generative auto-encoder based on bidirectional generative adversarial network (BiGAN). First, we introduce two terms that enhance information expansion in decoding to follow human visual models and to improve semantic-relevant feature representation capability in encoding. Furthermore, we embed a generative adversarial network (GAN) to improve representation while ensuring convergence. The experimental results show that Bi-GAE achieves competitive results in both generation and representation with stable convergence. Compared with its counterparts, the representational power of Bi-GAE improves the classification accuracy of high-resolution images by about 8.09%. In addition, Bi-GAE increases structural similarity index measure (SSIM) by 0.045, and decreases Fréchet inception distance (FID) by 2.48 in the reconstruction of 512 × 512 images.