Kepler Codebook

Junrong Lian, Ziyue Dong, Pengxu Wei, Wei Ke, Chang Liu, Qixiang Ye, Xiangyang Ji, Liang Lin

Research output: Contribution to journalConference articlepeer-review

Abstract

A codebook designed for learning discrete distributions in latent space has demonstrated state-of-the-art results on generation tasks. This inspires us to explore what distribution of codebook is better. Following the spirit of Kepler's Conjecture, we cast the codebook training as solving the sphere packing problem and derive a Kepler codebook with a compact and structured distribution to obtain a codebook for image representations. Furthermore, we implement the Kepler codebook training by simply employing this derived distribution as regularization and using the codebook partition method. We conduct extensive experiments to evaluate our trained codebook for image reconstruction and generation on natural and human face datasets, respectively, achieving significant performance improvement. Besides, our Kepler codebook has demonstrated superior performance when evaluated across datasets and even for reconstructing images with different resolutions. Codes and pre-trained weights are available at https://github.com/banianrong/KeplerCodebook.

Original languageEnglish
Pages (from-to)29511-29530
Number of pages20
JournalProceedings of Machine Learning Research
Volume235
Publication statusPublished - 2024
Externally publishedYes
Event41st International Conference on Machine Learning, ICML 2024 - Vienna, Austria
Duration: 21 Jul 202427 Jul 2024

Fingerprint

Dive into the research topics of 'Kepler Codebook'. Together they form a unique fingerprint.

Cite this