# Wavelet-Based Image Tokenizer for Vision Transformers

arXiv: https://arxiv.org/abs/2405.18616 · HTML: https://mlsanity.com/paper/2405.18616/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 66 references that are in the map.
- First posted on arXiv 28 May 2024.

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)

## Built on by (most cited first, 10 of 10)

- [DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space](https://mlsanity.com/paper/2412.15032/) (2024)
- [Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization](https://mlsanity.com/paper/2412.05244/) (2024)
- [When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization](https://mlsanity.com/paper/2412.16326/) (2024)
- [LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models](https://mlsanity.com/paper/2602.00135/) (2026)
- [Rethinking Brain Tumor Segmentation from the Frequency Domain Perspective](https://mlsanity.com/paper/2506.10142/) (2025)
- [Scaling Image Tokenizers with Grouped Spherical Quantization](https://mlsanity.com/paper/2412.02632/) (2024)
- [Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation](https://mlsanity.com/paper/2503.00782/) (2025)
- [WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP](https://mlsanity.com/paper/2509.21153/) (2025)
- [Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers](https://mlsanity.com/paper/2605.25949/) (2026)
- [Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals](https://mlsanity.com/paper/2606.02631/) (2026)

## Abstract (arXiv)

Non-overlapping patch-wise convolution is the default image tokenizer for all state-of-the-art vision Transformer (ViT) models. Even though many ViT variants have been proposed to improve its efficiency and accuracy, little research on improving the image tokenizer itself has been reported in the literature. In this paper, we propose a new image tokenizer based on wavelet transformation. We show that ViT models with the new tokenizer achieve both higher training throughput and better top-1 precision for the ImageNet validation set. We present a theoretical analysis on why the proposed tokenizer improves the training throughput without any change to ViT model architecture. Our analysis suggests that the new tokenizer can effectively handle high-resolution images and is naturally resistant to adversarial attack. Furthermore, the proposed image tokenizer offers a fresh perspective on important new research directions for ViT-based model design, such as image tokens on a non-uniform grid for image understanding.