paper-with-me

홈 › Papers

Physics-Informed Neural Network with Squeeze-Excitation-like Attention

2026-06-18 · Yun-Fei Song, Long-Gang Pang, Fu-Peng Li, Jun-Jie Zhang arxiv

We introduce SEA-PINN, a novel architecture that incorporates a Squeeze-Excitation-like attention mechanism into physics-informed neural networks to dynamically recalibrate the importance of neurons across layers. A key feature of SEA-PINN is its highly stable initialization. On 17 out of 20 benchmark problems, SEA-PINN exhibit nearly negligible variance and significantly reduced initial loss, establishing a quasi-deterministic and favorable starting point for optimization. Notably, without employing Fourier feature embeddings or periodic activation functions, SEA-PINN attained competitive accuracy (83\% vs. 90\% improvement relative to FNN-PINN on the high-frequency case 7) as compared with TSA-PINN-a model specifically engineered for high-frequency problems via learnable frequencies in sinusoidal activations. Furthermore, integrating SEA-PINN into TSA-PINN boosted performance by 42.49\%. These results underscore SEA-PINN as a lightweight plug-in module that enhances nonlinear representation power, promotes more robust and efficient convergence, and strengthens the overall reliability of physics-informed learning.

📄 PDF Abstract BibTeX arXiv:2606.19853

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Efficient Dilated Squeeze and Excitation Neural Operator for Differential Equations

2026-01-24 · Prajwal Chauhan, Salah Eddine Choutri, Saif Eddin Jabari arxiv

Fast and accurate surrogates for physics-driven partial differential equations (PDEs) are essential in fields such as aerodynamics, porous media design, and flow control. However, many transformer-based models and existi…

Squeeze Excitation Embedded Attention UNet for Brain Tumor Segmentation

2023-05-13 · Gaurav Prasanna, John Rohit Ernest, Lalitha G, Sathiya Narayanan

Deep Learning based techniques have gained significance over the past few years in the field of medicine. They are used in various applications such as classifying medical images, segmentation and identification. The exi…

Brain Tumor SegmentationSegmentationTumor Segmentation

SASE: A Searching Architecture for Squeeze and Excitation Operations

2024-11-13 · Hanming Wang, YunLong Li, Zijun Wu, Huifen Wang 외

In the past few years, channel-wise and spatial-wise attention blocks have been widely adopted as supplementary modules in deep neural networks, enhancing network representational abilities while introducing low complexi…

Neural Architecture Search

Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition

2021-12-21 · Xiangbo Shu, Jiawen Yang, Rui Yan, Yan Song

This work focuses on the task of elderly activity recognition, which is a challenging task due to the existence of individual actions and human-object interactions in elderly activities. Thus, we attempt to effectively a…

Action RecognitionActivity RecognitionHuman-Object Interaction Detection

MR Image Super-Resolution With Squeeze and Excitation Reasoning Attention Network

2021-06-19 · CVPR 2021 1 · Yulun Zhang, Kai Li, Kunpeng Li, Yun Fu

High-quality high-resolution (HR) magnetic resonance (MR) images afford more detailed information for reliable diagnosis and quantitative image analyses. Deep convolutional neural networks (CNNs) have shown promising…

Image Super-ResolutionSuper-Resolution