# Quantised Global Autoencoder: A Holistic Approach to Representing Visual Data

arXiv: https://arxiv.org/abs/2407.11913 · HTML: https://mlsanity.com/paper/2407.11913/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 40 references that are in the map.
- First posted on arXiv 16 Jul 2024.

## Builds on (most cited first, 18 of 18)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [An Image is Worth 32 Tokens for Reconstruction and Generation](https://mlsanity.com/paper/2406.07550/) (2024)
- [Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%](https://mlsanity.com/paper/2406.11837/) (2024)
- [Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization](https://mlsanity.com/paper/2305.11718/) (2023)
- [Robust Training of Vector Quantized Bottleneck Models](https://mlsanity.com/paper/2005.08520/) (2020)
- [Discrete Acoustic Space for an Efficient Sampling in Neural Text-To-Speech](https://mlsanity.com/paper/2110.12539/) (2021)

## Built on by (most cited first, 3 of 3)

- [Spectral Image Tokenizer](https://mlsanity.com/paper/2412.09607/) (2024)
- [Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation](https://mlsanity.com/paper/2411.10281/) (2024)
- [Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees](https://mlsanity.com/paper/2512.21857/) (2025)

## Abstract (arXiv)

In quantised autoencoders, images are usually split into local patches, each encoded by one token. This representation is redundant in the sense that the same number of tokens is spend per region, regardless of the visual information content in that region. Adaptive discretisation schemes like quadtrees are applied to allocate tokens for patches with varying sizes, but this just varies the region of influence for a token which nevertheless remains a local descriptor. Modern architectures add an attention mechanism to the autoencoder which infuses some degree of global information into the local tokens. Despite the global context, tokens are still associated with a local image region. In contrast, our method is inspired by spectral decompositions which transform an input signal into a superposition of global frequencies. Taking the data-driven perspective, we learn custom basis functions corresponding to the codebook entries in our VQ-VAE setup. Furthermore, a decoder combines these basis functions in a non-linear fashion, going beyond the simple linear superposition of spectral decompositions. We can achieve this global description with an efficient transpose operation between features and channels and demonstrate our performance on compression.