Object DGCNN: 3D Object Detection using Dynamic Graphs

Abstract

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.

Accepted to NeurIPS 2021

References in corpus (13)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Distilling the Knowledge in a Neural Network
• Decoupled Weight Decay Regularization
• A Simple Framework for Contrastive Learning of Visual Representations
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• Momentum Contrast for Unsupervised Visual Representation Learning
• Contrastive Multiview Coding
• Deep Continuous Fusion for Multi-Sensor 3D Object Detection
• FreeAnchor: Learning to Match Anchors for Visual Object Detection
• HDNET: Exploiting HD Maps for 3D Object Detection
• Rethinking ImageNet Pre-training
• Complex-YOLO: Real-time 3D Object Detection on Point Clouds
• Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection