paper-with-me

Papers

Structure-Preserving Transformers for Sequences of SPD Matrices

2023-09-14 · Mathieu Seraphim, Alexis Lechervy, Florian Yger, Luc Brun, Olivier Etard

In recent years, Transformer-based auto-attention mechanisms have been successfully applied to the analysis of a variety of context-reliant data types, from texts to images and beyond, including data from non-Euclidean geometries. In this paper, we present such a mechanism, designed to classify sequences of Symmetric Positive Definite matrices while preserving their Riemannian geometry throughout the analysis. We apply our method to automatic sleep staging on timeseries of EEG-derived covariance matrices from a standard dataset, obtaining high levels of stage-wise performance.

📄 PDF Abstract BibTeX arXiv:2309.07579

Code (2)

mathieuseraphim/spdtransnet 공식 구현 pytorch
MathieuSeraphim/SPDTransNet_plus pytorch

Tasks

EEGEEG based sleep stagingSleep Stage DetectionSleep Staging

Similar Papers 제목 키워드 기반

Privacy-Preserving Vision Transformer Using Images Encrypted with Restricted Random Permutation Matrices

2024-08-16 · Kouki Horio, Kiyoshi Nishikawa, Hitoshi Kiya

We propose a novel method for privacy-preserving fine-tuning vision transformers (ViTs) with encrypted images. Conventional methods using encrypted images degrade model performance compared with that of using plain image…

Privacy Preserving

MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention

2025-05-24 · Can Yaras, Alec S. Xu, Pierre Abillama, Changwoo Lee 외

Transformers have achieved state-of-the-art performance across various tasks, but suffer from a notable quadratic complexity in sequence length due to the attention mechanism. In this work, we propose MonarchAttention --…

16k4k

VMonarch: Efficient Video Diffusion Transformers with Structured Attention

2026-01-29 · Cheng Liang, Haoxian Chen, Liang Hou, Qi Fan 외 arxiv

The quadratic complexity of the attention mechanism severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the highly sparse spatio-temporal attention patterns exhibited in Video DiT…

Generating Long Sequences with Sparse Transformers

2019-04-23 · Preprint 2019 4 · Rewon Child, Scott Gray, Alec Radford, Ilya Sutskever

Transformers are powerful sequence models, but require time and memory that grows quadratically with the sequence length. In this paper we introduce sparse factorizations of the attention matrix which reduce this to $O(n…

DiversityImage GenerationLanguage ModellingOpen-Domain Question Answering+1

Exact Sequence Classification with Hardmax Transformers

2025-02-04 · Albert Alcalde, Giovanni Fantuzzi, Enrique Zuazua

We prove that hardmax attention transformers perfectly classify datasets of $N$ labeled sequences in $\mathbb{R}^d$, $d\geq 2$. Specifically, given $N$ sequences with an arbitrary but finite length in $\mathbb{R}^d$, we …

Classification