paper-with-me

홈 › Papers

Learning Local Receptive Fields and their Weight Sharing Scheme on Graphs

2017-06-08 · Jean-Charles Vialatte, Vincent Gripon, Gilles Coppin

We propose a simple and generic layer formulation that extends the properties of convolutional layers to any domain that can be described by a graph. Namely, we use the support of its adjacency matrix to design learnable weight sharing filters able to exploit the underlying structure of signals in the same fashion as for images. The proposed formulation makes it possible to learn the weights of the filter as well as a scheme that controls how they are shared across the graph. We perform validation experiments with image datasets and show that these filters offer performances comparable with convolutional ones.

📄 PDF Abstract BibTeX arXiv:1706.02684

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SPCTNet: A Series-Parallel CNN and Transformer Network for 3D Medical Image Segmentation

2024-02-04 · journal 2024 2 · Bin Yu, Quan Zhou & Xuming Zhang

Medical image segmentation is crucial for lesion localization and surgical navigation. Recent advancements in medical image segmentation have been driven by Convolutional Neural Networks (CNNs) and Transformers. However,…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Locally Smoothed Neural Networks

2017-11-22 · Liang Pang, Yanyan Lan, Jun Xu, Jiafeng Guo 외

Convolutional Neural Networks (CNN) and the locally connected layer are limited in capturing the importance and relations of different local receptive fields, which are often crucial for tasks such as face verification, …

Face VerificationQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolution

2026-03-12 · Cao Thien Tan, Phan Thi Thu Trang, Do Nghiem Duc, Ho Ngoc Anh 외 arxiv

Hybrid CNN-Transformer architectures achieve strong results in image super-resolution, but scaling attention windows or convolution kernels significantly increases computational cost, limiting deployment on resource-cons…

Image Super-ResolutionImage Restoration

Global2Local: Efficient Structure Search for Video Action Segmentation

2021-01-04 · CVPR 2021 1 · Shang-Hua Gao, Qi Han, Zhong-Yu Li, Pai Peng 외

Temporal receptive fields of models play an important role in action segmentation. Large receptive fields facilitate the long-term relations among video clips while small receptive fields help capture the local details. …

Action SegmentationSegmentation

SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers

2023-08-14 · Xijun Wang, Xiaojie Chu, Chunrui Han, Xiangyu Zhang

This paper presents a module, Spatial Cross-scale Convolution (SCSC), which is verified to be effective in improving both CNNs and Transformers. Nowadays, CNNs and Transformers have been successful in a variety of tasks.…

Face Recognition