Object DGCNN: 3D Object Detection using Dynamic Graphs

2021-10-13 · NeurIPS 2021 12 · Yue Wang, Justin Solomon

3D object detection often involves complicated training and testing pipelines, which require substantial domain knowledge about individual datasets. Inspired by recent non-maximum suppression-free 2D object detection models, we propose a 3D object detection architecture on point clouds. Our method models 3D object detection as message passing on a dynamic graph, generalizing the DGCNN framework to predict a set of objects. In our construction, we remove the necessity of post-processing via object confidence aggregation or non-maximum suppression. To facilitate object detection from sparse point clouds, we also propose a set-to-set distillation approach customized to 3D detection. This approach aligns the outputs of the teacher model and the student model in a permutation-invariant fashion, significantly simplifying knowledge distillation for the 3D detection task. Our method achieves state-of-the-art performance on autonomous driving benchmarks. We also provide abundant analysis of the detection model and distillation framework.

📄 PDF Abstract BibTeX arXiv:2110.06923

Code (1)

wangyueft/detr3d 공식 구현 pytorch

Tasks

2D Object Detection 3D Object Detection Autonomous Driving Knowledge DistillationObjectobject-detection Object Detection

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

DGCNN 설명 없음

Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features

2019-04-22 · Kuangen Zhang, Ming Hao, Jing Wang, Clarence W. de Silva 외

Learning on point cloud is eagerly in demand because the point cloud is a common type of geometric data and can aid robots to understand environments robustly. However, the point cloud is sparse, unstructured, and unorde…

A Tiny Machine Learning Model for Point Cloud Object Classification

2023-03-20 · Min Zhang, Jintang Xue, Pranav Kadam, Hardik Prajapati 외

The design of a tiny machine learning model, which can be deployed in mobile and edge devices, for point cloud object classification is investigated in this work. To achieve this objective, we replace the multi-scale rep…

Object

A Scalable Approach for Outlier Detection in Edge Streams Using Sketch-based Approximations

2016-05-07 · SDM 2016 2016 5 · Stephen Ranshous, Steve Harenberg, Kshitij Sharma, Nagiza F. Samatova

Dynamic graphs are a powerful way to model an evolving set of objects and their ongoing interactions. A broad spectrum of systems, such as information, communication, and social, are naturally represented by dynamic grap…

Anomaly Detection Anomaly Detection in Edge Streams Outlier Detection

DrivAerNet: A Parametric Car Dataset for Data-Driven Aerodynamic Design and Prediction

2024-03-12 · Mohamed Elrefaie, Angela Dai, Faez Ahmed

This study introduces DrivAerNet, a large-scale high-fidelity CFD dataset of 3D industry-standard car shapes, and RegDGCNN, a dynamic graph convolutional neural network model, both aimed at aerodynamic car design through…

Relation Parsing Neural Network for Human-Object Interaction Detection

2019-10-01 · ICCV 2019 10 · Penghao Zhou, Mingmin Chi

Human-Object Interaction Detection devotes to infer a triplet < human, verb, object > between human and objects. In this paper, we propose a novel model, i.e., Relation Parsing Neural Network (RPNN), to detect human-obje…

Human-Object Interaction Detection Object Relation Triplet