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 language | English |
---|---|
Pages (from-to) | 29511-29530 |
Number of pages | 20 |
Journal | Proceedings of Machine Learning Research |
Volume | 235 |
Publication status | Published - 2024 |
Externally published | Yes |
Event | 41st International Conference on Machine Learning, ICML 2024 - Vienna, Austria Duration: 21 Jul 2024 → 27 Jul 2024 |