paper-with-me

홈 › Papers

Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals

2026-05-30 · Shenghao Ding arxiv

This paper studies whether audio, images, and video can share a common wavelet token schema rather than relying on separate modality-specific latent grids. It introduces a preliminary continuous-token model built around a one-level Haar DWT/IDWT frontend, a shared coefficient-token layout, optional structural metadata, lightweight modality value adapters, and a shared token-wise encoder-decoder trunk. On Speech Commands, EuroSAT RGB, and DAVIS 2017 data, a dense shared model reaches 39.92 dB audio, 29.37 dB image, and 23.93 dB video PSNR. A matched-rate sweep under continuous latent scalar budgets indicates that the visual gains are not explained solely by latent capacity, while also showing that additive metadata embeddings are not a universal source of improvement. Finally, fixed-rate energy selection provides a strong non-parametric baseline: energy_global improves average PSNR over uniform selection by 16.73 dB for audio, 16.90 dB for images, and 15.86 dB for video under compressed keep ratios. Masked sparse training reaches 34.45 dB video PSNR with 50% of dense tokens. The results support a unified wavelet token schema and sparse token interface, while stopping short of establishing a universal discrete vocabulary.

📄 PDF Abstract BibTeX arXiv:2606.02631

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Wavelet-Based Image Tokenizer for Vision Transformers

2024-05-28 · Zhenhai Zhu, Radu Soricut

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, lit…

Adversarial Attack

WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series Forecasting

2026-04-12 · Shunyu Wu, Jiawei Huang, Weibin Feng, Boxin Li 외 arxiv

Time series foundation models (TSFMs) have recently achieved remarkable success in universal forecasting by leveraging large-scale pretraining on diverse time series data. Complementing this progress, incorporating frequ…

Time Series Forecasting

A new image compression by gradient Haar wavelet

2017-04-28 · Yaser Sadra

With the development of human communications the usage of Visual Communications has also increased. The advancement of image compression methods is one of the main reasons for the enhancement. This paper first presents m…

Image CompressionSSIM

Deep Learning in the Wavelet Domain

2018-11-14 · Fergal Cotter, Nick Kingsbury

This paper examines the possibility of, and the possible advantages to learning the filters of convolutional neural networks (CNNs) for image analysis in the wavelet domain. We are stimulated by both Mallat's scattering …

Deep Learning

Fault Detection and Classification using Wavelet and ANN in DFIG and TCSC Connected Transmission Line

2023-08-17 · Satya Vikram Pratap Singh, Tanu Prasad, Siddharth Kamila, Prashant Agnihotri

This paper presents fault detection and classification using Wavelet and ANN based methods in a DFIG-based series compensated system. The state-of-the art methods include Wavelet transform, Fourier transform, and Wavelet…

Fault Detection