Vector Quantized Wasserstein Auto-Encoder

• Published in: arXiv.org
• Main Authors: Tung-Long Vuong, Le, Trung, Zhao, He, Zheng, Chuanxia, Harandi, Mehrtash, Cai, Jianfei, Dinh Phung
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 17.06.2023
• Subjects: Clustering; Coders; Controllability; Image reconstruction; Learning; Representations

Learning deep discrete latent presentations offers a promise of better symbolic and summarized abstractions that are more useful to subsequent downstream tasks. Inspired by the seminal Vector Quantized Variational Auto-Encoder (VQ-VAE), most of work in learning deep discrete representations has main...