SCKD: Semi-Supervised Cross-Modality Knowledge Distillation for 4D Radar Object Detection

• URL: http://arxiv.org/abs/2412.14571v1
• Date: Thu, 19 Dec 2024 06:42:25 GMT
• Title: SCKD: Semi-Supervised Cross-Modality Knowledge Distillation for 4D Radar Object Detection
• Authors: Ruoyu Xu, Zhiyu Xiang, Chenwei Zhang, Hanzhi Zhong, Xijun Zhao, Ruina Dang, Peng Xu, Tianyu Pu, Eryun Liu,
• Abstract summary: We propose a novel Semi-supervised Cross-modality Knowledge Distillation (SCKD) method for 4D radar-based 3D object detection. It characterizes the capability of learning the feature from a Lidar-radar-fused teacher network with semi-supervised distillation. With the same network structure, our radar-only student trained by SCKD boosts the mAP by 10.38% over the baseline.
• Score: 16.127926058992237
• License:
• Abstract: 3D object detection is one of the fundamental perception tasks for autonomous vehicles. Fulfilling such a task with a 4D millimeter-wave radar is very attractive since the sensor is able to acquire 3D point clouds similar to Lidar while maintaining robust measurements under adverse weather. However, due to the high sparsity and noise associated with the radar point clouds, the performance of the existing methods is still much lower than expected. In this paper, we propose a novel Semi-supervised Cross-modality Knowledge Distillation (SCKD) method for 4D radar-based 3D object detection. It characterizes the capability of learning the feature from a Lidar-radar-fused teacher network with semi-supervised distillation. We first propose an adaptive fusion module in the teacher network to boost its performance. Then, two feature distillation modules are designed to facilitate the cross-modality knowledge transfer. Finally, a semi-supervised output distillation is proposed to increase the effectiveness and flexibility of the distillation framework. With the same network structure, our radar-only student trained by SCKD boosts the mAP by 10.38% over the baseline and outperforms the state-of-the-art works on the VoD dataset. The experiment on ZJUODset also shows 5.12% mAP improvements on the moderate difficulty level over the baseline when extra unlabeled data are available. Code is available at https://github.com/Ruoyu-Xu/SCKD.

Related papers

• A Novel Multi-Teacher Knowledge Distillation for Real-Time Object Detection using 4D Radar [5.038148262901536]
  3D object detection is crucial for safe autonomous navigation, requiring reliable performance across diverse weather conditions. Traditional Radars have limitations due to their lack of elevation data. 4D Radars overcome this by measuring elevation alongside range, azimuth, and Doppler velocity, making them invaluable for autonomous vehicles.
  arXiv  Detail & Related papers  (2025-02-10T02:48:56Z)
• MSSF: A 4D Radar and Camera Fusion Framework With Multi-Stage Sampling for 3D Object Detection in Autonomous Driving [9.184945917823047]
  We present a simple but effective multi-stage sampling fusion (MSSF) network based on 4D radar and camera. MSSF achieves a 7.0% and 4.0% improvement in 3D mean average precision on the View-of-Delft (VoD) and TJ4DRadset datasets. It even surpasses classical LiDAR-based methods on the VoD dataset.
  arXiv  Detail & Related papers  (2024-11-22T15:45:23Z)
• UniBEVFusion: Unified Radar-Vision BEVFusion for 3D Object Detection [2.123197540438989]
  Many radar-vision fusion models treat radar as a sparse LiDAR, underutilizing radar-specific information. We propose the Radar Depth Lift-Splat-Shoot (RDL) module, which integrates radar-specific data into the depth prediction process. We also introduce a Unified Feature Fusion (UFF) approach that extracts BEV features across different modalities.
  arXiv  Detail & Related papers  (2024-09-23T06:57:27Z)
• LEROjD: Lidar Extended Radar-Only Object Detection [0.22870279047711525]
  3+1D imaging radar sensors offer a cost-effective, robust alternative to lidar. Although lidar should not be used during inference, it can aid the training of radar-only object detectors. We explore two strategies to transfer knowledge from the lidar to the radar domain and radar-only object detectors.
  arXiv  Detail & Related papers  (2024-09-09T12:43:25Z)
• 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)
• 4D Contrastive Superflows are Dense 3D Representation Learners [62.433137130087445]
  We introduce SuperFlow, a novel framework designed to harness consecutive LiDAR-camera pairs for establishing pretraining objectives. To further boost learning efficiency, we incorporate a plug-and-play view consistency module that enhances alignment of the knowledge distilled from camera views.
  arXiv  Detail & Related papers  (2024-07-08T17:59:54Z)
• Boosting 3D Object Detection by Simulating Multimodality on Point Clouds [51.87740119160152]
  This paper presents a new approach to boost a single-modality (LiDAR) 3D object detector by teaching it to simulate features and responses that follow a multi-modality (LiDAR-image) detector. The approach needs LiDAR-image data only when training the single-modality detector, and once well-trained, it only needs LiDAR data at inference. Experimental results on the nuScenes dataset show that our approach outperforms all SOTA LiDAR-only 3D detectors.
  arXiv  Detail & Related papers  (2022-06-30T01:44:30Z)
• MonoDistill: Learning Spatial Features for Monocular 3D Object Detection [80.74622486604886]
  We propose a simple and effective scheme to introduce the spatial information from LiDAR signals to the monocular 3D detectors. We use the resulting data to train a 3D detector with the same architecture as the baseline model. Experimental results show that the proposed method can significantly boost the performance of the baseline model.
  arXiv  Detail & Related papers  (2022-01-26T09:21:41Z)
• The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection [62.1185839286255]
  Low-cost monocular 3D object detection plays a fundamental role in autonomous driving. We introduce a Dynamic Feature Reflecting Network, named DFR-Net. We rank 1st among all the monocular 3D object detectors in the KITTI test set.
  arXiv  Detail & Related papers  (2021-12-28T07:31:18Z)
• Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud [79.39041453836793]
  We develop a novel single-stage 3D detector for point clouds in an anchor-free manner. We overcome this by converting the voxel-based sparse 3D feature volumes into the sparse 2D feature maps. We propose an IoU-based detection confidence re-calibration scheme to improve the correlation between the detection confidence score and the accuracy of the bounding box regression.
  arXiv  Detail & Related papers  (2021-08-08T13:42:13Z)
• D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features [51.04841465193678]
  We leverage a 3D fully convolutional network for 3D point clouds. We propose a novel and practical learning mechanism that densely predicts both a detection score and a description feature for each 3D point. Our method achieves state-of-the-art results in both indoor and outdoor scenarios.
  arXiv  Detail & Related papers  (2020-03-06T12:51:09Z)

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.