paper-with-me

Papers

Graph-Instructed Neural Networks for Sparse Grid-Based Discontinuity Detectors

2024-01-24 · Francesco Della Santa, Sandra Pieraccini

In this paper, we present a novel approach for detecting the discontinuity interfaces of a discontinuous function. This approach leverages Graph-Instructed Neural Networks (GINNs) and sparse grids to address discontinuity detection also in domains of dimension larger than 3. GINNs, trained to identify troubled points on sparse grids, exploit graph structures built on the grids to achieve efficient and accurate discontinuity detection performances. We also introduce a recursive algorithm for general sparse grid-based detectors, characterized by convergence properties and easy applicability. Numerical experiments on functions with dimensions n = 2 and n = 4 demonstrate the efficiency and robust generalization properties of GINNs in detecting discontinuity interfaces. Notably, the trained GINNs offer portability and versatility, allowing integration into various algorithms and sharing among users.

📄 PDF Abstract BibTeX arXiv:2401.13652

Code (2)

fra0013to/nnbaseddiscdetectors 공식 구현 tf
fra0013to/ginn tf

Similar Papers 제목 키워드 기반

Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph

2022-08-07 · Honghui Yang, Zili Liu, Xiaopei Wu, Wenxiao Wang 외

Two-stage detectors have gained much popularity in 3D object detection. Most two-stage 3D detectors utilize grid points, voxel grids, or sampled keypoints for RoI feature extraction in the second stage. Such methods, how…

3D Object Detectionobject-detectionObject Detection

Dense Label Encoding for Boundary Discontinuity Free Rotation Detection

2020-11-19 · CVPR 2021 1 · Xue Yang, Liping Hou, Yue Zhou, Wentao Wang 외

Rotation detection serves as a fundamental building block in many visual applications involving aerial image, scene text, and face etc. Differing from the dominant regression-based approaches for orientation estimation, …

ClassificationGeneral ClassificationObject Detection In Aerial Imagesregression

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

2023-08-18 · ICCV 2023 1 · Shenghao Fu, Junkai Yan, Yipeng Gao, Xiaohua Xie 외

Recent sparse detectors with multiple, e.g. six, decoder layers achieve promising performance but much inference time due to complex heads. Previous works have explored using dense priors as initialization and built one-…

Decoder

Graph Query Networks for Object Detection with Automotive Radar

2025-11-19 · Loveneet Saini, Hasan Tercan, Tobias Meisen arxiv

Object detection with 3D radar is essential for 360-degree automotive perception, but radar's long wavelengths produce sparse and irregular reflections that challenge traditional grid and sequence-based convolutional and…

Relational ReasoningObject Detection

Edge-Wise Graph-Instructed Neural Networks

2024-09-12 · Francesco Della Santa, Antonio Mastropietro, Sandra Pieraccini, Francesco Vaccarino

The problem of multi-task regression over graph nodes has been recently approached through Graph-Instructed Neural Network (GINN), which is a promising architecture belonging to the subset of message-passing graph neural…