Learning Local Receptive Fields and their Weight Sharing Scheme on Graphs
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SPCTNet: A Series-Parallel CNN and Transformer Network for 3D Medical Image Segmentation
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 SegmentationLocally Smoothed Neural Networks
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
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 RestorationGlobal2Local: Efficient Structure Search for Video Action Segmentation
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 SegmentationSegmentationSCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers
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