paper-with-me

Papers

Harmformer: Harmonic Networks Meet Transformers for Continuous Roto-Translation Equivariance

2024-11-06 · Tomáš Karella, Adam Harmanec, Jan Kotera, Jan Blažek, Filip Šroubek

CNNs exhibit inherent equivariance to image translation, leading to efficient parameter and data usage, faster learning, and improved robustness. The concept of translation equivariant networks has been successfully extended to rotation transformation using group convolution for discrete rotation groups and harmonic functions for the continuous rotation group encompassing $360^\circ$. We explore the compatibility of the SA mechanism with full rotation equivariance, in contrast to previous studies that focused on discrete rotation. We introduce the Harmformer, a harmonic transformer with a convolutional stem that achieves equivariance for both translation and continuous rotation. Accompanied by an end-to-end equivariance proof, the Harmformer not only outperforms previous equivariant transformers, but also demonstrates inherent stability under any continuous rotation, even without seeing rotated samples during training.

📄 PDF Abstract BibTeX arXiv:2411.03794

Code (0)

등록된 구현이 없습니다.

Tasks

Translation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs

2025-05-04 · Sai Krishna Mendu, Harish Yenala, Aditi Gulati, Shanu Kumar 외

Large language models (LLMs) have become integral to various real-world applications, leveraging massive, web-sourced datasets like Common Crawl, C4, and FineWeb for pretraining. While these datasets provide linguistic d…

MisinformationText Generation

Oscillators Are All You Need: Irregular Time Series Modelling via Damped Harmonic Oscillators with Closed-Form Solutions

2026-02-12 · Yashas Shende, Aritra Das, Reva Laxmi Chauhan, Arghya Pathak 외 arxiv

Transformers excel at time series modelling through attention mechanisms that capture long-term temporal patterns. However, they assume uniform time intervals and therefore struggle with irregular time series. Neural Ord…

How Do Transformers "Do" Physics? Investigating the Simple Harmonic Oscillator

2024-05-23 · Subhash Kantamneni, Ziming Liu, Max Tegmark

How do transformers model physics? Do transformers model systems with interpretable analytical solutions, or do they create "alien physics" that are difficult for humans to decipher? We take a step in demystifying this l…

The Fractal Neural Operator: Overcoming Spectral Bias in Chaotic Attractors via Prime-Harmonic Weierstrass Encodings

2026-06-22 · Kanishk Awadhiya arxiv

Deep learning models, particularly Transformers and Neural Operators, exhibit a well-documented "spectral bias," effectively acting as low-pass filters that smooth out high-frequency information. While benign in fluid dy…

Multi-microphone Automatic Speech Segmentation in Meetings Based on Circular Harmonics Features

2023-06-07 · Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas

Speaker diarization is the task of answering Who spoke and when? in an audio stream. Pipeline systems rely on speech segmentation to extract speakers' segments and achieve robust speaker diarization. This paper proposes …

Action DetectionActivity DetectionChange DetectionSegmentation+2