AFDet: Anchor Free One Stage 3D Object Detection
arXiv:2006.12671
Abstract
High-efficiency point cloud 3D object detection operated on embedded systems is important for many robotics applications including autonomous driving. Most previous works try to solve it using anchor-based detection methods which come with two drawbacks: post-processing is relatively complex and computationally expensive; tuning anchor parameters is tricky. We are the first to address these drawbacks with an anchor free and Non-Maximum Suppression free one stage detector called AFDet. The entire AFDet can be processed efficiently on a CNN accelerator or a GPU with the simplified post-processing. Without bells and whistles, our proposed AFDet performs competitively with other one stage anchor-based methods on KITTI validation set and Waymo Open Dataset validation set.
Accepted on May 6th, 2020 by CVPRW 2020, published on June 7th, 2020; Baseline detector for the 1st place solutions of Waymo Open Dataset Challenges 2020
References in corpus (10)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Decoupled Weight Decay Regularization
- Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
- Scalability in Perception for Autonomous Driving: Waymo Open Dataset
- Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
- StarNet: Targeted Computation for Object Detection in Point Clouds
- End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds
- RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving
- Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
- Improving 3D Object Detection through Progressive Population Based Augmentation
Cited by in corpus (22)
- Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting
- Center-based 3D Object Detection and Tracking
- CenterNet3D: An Anchor Free Object Detector for Point Cloud
- 3D Object Tracking with Transformer
- 3D-LaneNet+: Anchor Free Lane Detection using a Semi-Local Representation
- Pattern-Aware Data Augmentation for LiDAR 3D Object Detection
- 1st Place Solution for Waymo Open Dataset Challenge -- 3D Detection and Domain Adaptation
- Multi-Modal 3D Object Detection in Autonomous Driving: a Survey
- PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds
- Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection
- 1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking
- RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
- OST: Efficient One-stream Network for 3D Single Object Tracking in Point Clouds
- Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness
- Voxel Transformer for 3D Object Detection
- Pseudo-labeling for Scalable 3D Object Detection
- 3D-MAN: 3D Multi-frame Attention Network for Object Detection
- LiDAR R-CNN: An Efficient and Universal 3D Object Detector
- Scalable Primitives for Generalized Sensor Fusion in Autonomous Vehicles
- From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection
- 3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds
- A two-stage data association approach for 3D Multi-object Tracking