LL-VQ-VAE: Learnable Lattice Vector-Quantization For Efficient Representations

2023/10/13 by Khalil, Ahmed, Piechocki, Robert, Santos-Rodriguez, Raul · 2 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2310.09382

Abstract

In this paper we introduce learnable lattice vector quantization and demonstrate its effectiveness for learning discrete representations. Our method, termed LL-VQ-VAE, replaces the vector quantization layer in VQ-VAE with lattice-based discretization. The learnable lattice imposes a structure over all discrete embeddings, acting as a deterrent against codebook collapse, leading to high codebook utilization. Compared to VQ-VAE, our method obtains lower reconstruction errors under the same training conditions, trains in a fraction of the time, and with a constant number of parameters (equal to the embedding dimension D), making it a very scalable approach. We demonstrate these results on the FFHQ-1024 dataset and include FashionMNIST and Celeb-A.

Cited by

• Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression
• Receptive Field Expanded Look-Up Tables for Vision Inference: Advancing from Low-level to High-level Tasks

Related

• Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression
• Lattice Representation Learning
• Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
• Finite Scalar Quantization: VQ-VAE Made Simple
• The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm