Document detail
ID

oai:arXiv.org:2404.14674

Topic
Computer Science - Machine Learnin... Computer Science - Artificial Inte... Computer Science - Computer Vision... Computer Science - Multimedia
Author
Chen, Yang Wu, Ruituo Liu, Yipeng Zhu, Ce
Category

Computer Science

Year

2024

listing date

5/1/2024

Keywords
implicit representations neural inverse science computer
Metrics

Abstract

Implicit neural representations (INR) suffer from worsening spectral bias, which results in overly smooth solutions to the inverse problem.

To deal with this problem, we propose a universal framework for processing inverse problems called \textbf{High-Order Implicit Neural Representations (HOIN)}.

By refining the traditional cascade structure to foster high-order interactions among features, HOIN enhances the model's expressive power and mitigates spectral bias through its neural tangent kernel's (NTK) strong diagonal properties, accelerating and optimizing inverse problem resolution.

By analyzing the model's expression space, high-order derivatives, and the NTK matrix, we theoretically validate the feasibility of HOIN.

HOIN realizes 1 to 3 dB improvements in most inverse problems, establishing a new state-of-the-art recovery quality and training efficiency, thus providing a new general paradigm for INR and paving the way for it to solve the inverse problem.

Chen, Yang,Wu, Ruituo,Liu, Yipeng,Zhu, Ce, 2024, HOIN: High-Order Implicit Neural Representations

Document

Open

Share

Source

Articles recommended by ES/IODE AI

Acceptability of self-collected vaginal samples for human papillomavirus testing for primary cervical cancer screening: comparison of face-to-face and online recruitment modes
human papillomavirus cervical cancer screening self-sampling screening cervical cancer 1% uptake rate website acceptability online face-to-face participants