Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness

by   Runzhou Ge, et al.

In this report, we introduce our winning solution to the Real-time 3D Detection and also the "Most Efficient Model" in the Waymo Open Dataset Challenges at CVPR 2021. Extended from our last year's award-winning model AFDet, we have made a handful of modifications to the base model, to improve the accuracy and at the same time to greatly reduce the latency. The modified model, named as AFDetV2, is featured with a lite 3D Feature Extractor, an improved RPN with extended receptive field and an added sub-head that produces an IoU-aware confidence score. These model enhancements, together with enriched data augmentation, stochastic weights averaging, and a GPU-based implementation of voxelization, lead to a winning accuracy of 73.12 mAPH/L2 for our AFDetV2 with a latency of 60.06 ms, and an accuracy of 72.57 mAPH/L2 for our AFDetV2-base, entitled as the "Most Efficient Model" by the challenge sponsor, with a winning latency of 55.86 ms.


page 3

page 6


CenterAtt: Fast 2-stage Center Attention Network

In this technical report, we introduce the methods of HIKVISION_LiDAR_De...

2nd Place Solution for Waymo Open Dataset Challenge – Real-time 2D Object Detection

In an autonomous driving system, it is essential to recognize vehicles, ...

Optimizing Anchor-based Detectors for Autonomous Driving Scenes

This paper summarizes model improvements and inference-time optimization...

A Latency-Aware Real-Time Video Surveillance Demo: Network Slicing for Improving Public Safety

We report the automated deployment of 5G services across a latency-aware...

Minimum Latency Training of Sequence Transducers for Streaming End-to-End Speech Recognition

Sequence transducers, such as the RNN-T and the Conformer-T, are one of ...

Fast and Efficient Model for Real-Time Tiger Detection In The Wild

The highest accuracy object detectors to date are based either on a two-...

Plane Sweep Algorithms for Data Collection in Wireless Sensor Network using Mobile Sink

Usage of mobile sink(s) for data gathering in wireless sensor networks(W...

Please sign up or login with your details

Forgot password? Click here to reset