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

2021-07-29 · Runzhou Ge, Zhuangzhuang Ding, Yihan Hu, Wenxin Shao, Li Huang, Kun Li, Qiang Liu

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.

📄 PDF Abstract BibTeX arXiv:2107.14342

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationGPU

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

SAPD：Soft Anchor-Point Detector

2019-11-27 · arXiv 2019 11 · Chenchen Zhu, Fangyi Chen, Zhiqiang Shen, Marios Savvides

Recently, anchor-free detectors have shown great potential to outperform anchor-based detectors in terms of both accuracy and speed. In this work, we aim at finding a new balance of speed and accuracy for anchor-free det…

feature selection Object Detection

Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud

2021-08-08 · Jiale Li, Hang Dai, Ling Shao, Yong Ding

Most of the existing single-stage and two-stage 3D object detectors are anchor-based methods, while the efficient but challenging anchor-free single-stage 3D object detection is not well investigated. Recent studies on 2…

2D Object Detection 3D Object Detection Object object-detection+1

FCOS: Fully Convolutional One-Stage Object Detection

2019-04-02 · ICCV 2019 10 · Zhi Tian, Chunhua Shen, Hao Chen, Tong He

We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object detectors such as Retin…

2D Object Detection Object Object Detection Pedestrian Detection+1

CenterNet3D: An Anchor Free Object Detector for Point Cloud

2020-07-13 · Guojun Wang, Jian Wu, Bin Tian, Siyu Teng 외

Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based d…

3D Object Detection Autonomous Driving Keypoint Estimation Object+2

Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection

2021-04-29 · Jiachen Li, Bowen Cheng, Rogerio Feris, JinJun Xiong 외

Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-design…

Object object-detection Object Detection