RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features
- URL: http://arxiv.org/abs/2403.05061v2
- Date: Fri, 5 Apr 2024 00:43:16 GMT
- Title: RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features
- Authors: Geonho Bang, Kwangjin Choi, Jisong Kim, Dongsuk Kum, Jun Won Choi,
- Abstract summary: RadarDistill is a knowledge distillation (KD) method which can improve the representation of radar data by leveraging LiDAR data.
RadarDistill successfully transfers desirable characteristics of LiDAR features into radar features using three key components.
Our comparative analyses conducted on the nuScenes datasets demonstrate that RadarDistill achieves state-of-the-art (SOTA) performance for radar-only object detection task.
- Score: 15.686167262542297
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The inherent noisy and sparse characteristics of radar data pose challenges in finding effective representations for 3D object detection. In this paper, we propose RadarDistill, a novel knowledge distillation (KD) method, which can improve the representation of radar data by leveraging LiDAR data. RadarDistill successfully transfers desirable characteristics of LiDAR features into radar features using three key components: Cross-Modality Alignment (CMA), Activation-based Feature Distillation (AFD), and Proposal-based Feature Distillation (PFD). CMA enhances the density of radar features by employing multiple layers of dilation operations, effectively addressing the challenge of inefficient knowledge transfer from LiDAR to radar. AFD selectively transfers knowledge based on regions of the LiDAR features, with a specific focus on areas where activation intensity exceeds a predefined threshold. PFD similarly guides the radar network to selectively mimic features from the LiDAR network within the object proposals. Our comparative analyses conducted on the nuScenes datasets demonstrate that RadarDistill achieves state-of-the-art (SOTA) performance for radar-only object detection task, recording 20.5% in mAP and 43.7% in NDS. Also, RadarDistill significantly improves the performance of the camera-radar fusion model.
Related papers
- RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection [68.99784784185019]
Poor lighting or adverse weather conditions degrade camera performance.
Radar suffers from noise and positional ambiguity.
We propose RobuRCDet, a robust object detection model in BEV.
arXiv Detail & Related papers (2025-02-18T17:17:38Z) - TransRAD: Retentive Vision Transformer for Enhanced Radar Object Detection [6.163747364795787]
We present TransRAD, a novel 3D radar object detection model.
We propose Location-Aware NMS to mitigate the common issue of duplicate bounding boxes in deep radar object detection.
Results demonstrate that TransRAD outperforms state-of-the-art methods in both 2D and 3D radar detection tasks.
arXiv Detail & Related papers (2025-01-29T20:21:41Z) - MutualForce: Mutual-Aware Enhancement for 4D Radar-LiDAR 3D Object Detection [3.1212590312985986]
We propose a 4D radar-LiDAR framework to mutually enhance their representations.
First, the indicative features from radar are utilized to guide both radar and LiDAR geometric feature learning.
To mitigate their sparsity gap, the shape information from LiDAR is used to enrich radar BEV features.
arXiv Detail & Related papers (2025-01-17T15:48:37Z) - RadarPillars: Efficient Object Detection from 4D Radar Point Clouds [42.9356088038035]
We present RadarPillars, a pillar-based object detection network.
By decomposing radial velocity data, RadarPillars significantly outperform state-of-the-art detection results on the View-of-Delft dataset.
This comes at a significantly reduced parameter count, surpassing existing methods in terms of efficiency and enabling real-time performance on edge devices.
arXiv Detail & Related papers (2024-08-09T12:13:38Z) - Radar Fields: Frequency-Space Neural Scene Representations for FMCW Radar [62.51065633674272]
We introduce Radar Fields - a neural scene reconstruction method designed for active radar imagers.
Our approach unites an explicit, physics-informed sensor model with an implicit neural geometry and reflectance model to directly synthesize raw radar measurements.
We validate the effectiveness of the method across diverse outdoor scenarios, including urban scenes with dense vehicles and infrastructure.
arXiv Detail & Related papers (2024-05-07T20:44:48Z) - Better Monocular 3D Detectors with LiDAR from the Past [64.6759926054061]
Camera-based 3D detectors often suffer inferior performance compared to LiDAR-based counterparts due to inherent depth ambiguities in images.
In this work, we seek to improve monocular 3D detectors by leveraging unlabeled historical LiDAR data.
We show consistent and significant performance gain across multiple state-of-the-art models and datasets with a negligible additional latency of 9.66 ms and a small storage cost.
arXiv Detail & Related papers (2024-04-08T01:38:43Z) - Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object
Detection [78.59426158981108]
We introduce a bi-directional LiDAR-Radar fusion framework, termed Bi-LRFusion, to tackle the challenges and improve 3D detection for dynamic objects.
We conduct extensive experiments on nuScenes and ORR datasets, and show that our Bi-LRFusion achieves state-of-the-art performance for detecting dynamic objects.
arXiv Detail & Related papers (2023-06-02T10:57:41Z) - LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar
Fusion [52.59664614744447]
We present LiRaNet, a novel end-to-end trajectory prediction method which utilizes radar sensor information along with widely used lidar and high definition (HD) maps.
automotive radar provides rich, complementary information, allowing for longer range vehicle detection as well as instantaneous velocity measurements.
arXiv Detail & Related papers (2020-10-02T00:13:00Z) - RadarNet: Exploiting Radar for Robust Perception of Dynamic Objects [73.80316195652493]
We tackle the problem of exploiting Radar for perception in the context of self-driving cars.
We propose a new solution that exploits both LiDAR and Radar sensors for perception.
Our approach, dubbed RadarNet, features a voxel-based early fusion and an attention-based late fusion.
arXiv Detail & Related papers (2020-07-28T17:15:02Z) - Probabilistic Oriented Object Detection in Automotive Radar [8.281391209717103]
We propose a deep-learning based algorithm for radar object detection.
We created a new multimodal dataset with 102544 frames of raw radar and synchronized LiDAR data.
Our best performing radar detection model achieves 77.28% AP under oriented IoU of 0.3.
arXiv Detail & Related papers (2020-04-11T05:29:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.