StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection

• URL: http://arxiv.org/abs/2301.01615v1
• Date: Wed, 4 Jan 2023 13:38:48 GMT
• Title: StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection
• Authors: Zhe Liu, Xiaoqing Ye, Xiao Tan, Errui Ding, Xiang Bai
• Abstract summary: We propose a cross-modal distillation method named StereoDistill to narrow the gap between the stereo and LiDAR-based approaches. Key designs of StereoDistill are: the X-component Guided Distillation(XGD) for regression and the Cross-anchor Logit Distillation(CLD) for classification.
• Score: 93.10989714186788
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose a cross-modal distillation method named StereoDistill to narrow the gap between the stereo and LiDAR-based approaches via distilling the stereo detectors from the superior LiDAR model at the response level, which is usually overlooked in 3D object detection distillation. The key designs of StereoDistill are: the X-component Guided Distillation~(XGD) for regression and the Cross-anchor Logit Distillation~(CLD) for classification. In XGD, instead of empirically adopting a threshold to select the high-quality teacher predictions as soft targets, we decompose the predicted 3D box into sub-components and retain the corresponding part for distillation if the teacher component pilot is consistent with ground truth to largely boost the number of positive predictions and alleviate the mimicking difficulty of the student model. For CLD, we aggregate the probability distribution of all anchors at the same position to encourage the highest probability anchor rather than individually distill the distribution at the anchor level. Finally, our StereoDistill achieves state-of-the-art results for stereo-based 3D detection on the KITTI test benchmark and extensive experiments on KITTI and Argoverse Dataset validate the effectiveness.

Related papers

• Understanding Self-Distillation and Partial Label Learning in Multi-Class Classification with Label Noise [12.636657455986144]
  Self-distillation (SD) is the process of training a student model using the outputs of a teacher model. Our study theoretically examines SD in multi-class classification with cross-entropy loss.
  arXiv  Detail & Related papers  (2024-02-16T07:13:12Z)
• Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection [77.23918785277404]
  We present Diffusion-SS3D, a new perspective of enhancing the quality of pseudo-labels via the diffusion model for semi-supervised 3D object detection. Specifically, we include noises to produce corrupted 3D object size and class label, distributions, and then utilize the diffusion model as a denoising process to obtain bounding box outputs. We conduct experiments on the ScanNet and SUN RGB-D benchmark datasets to demonstrate that our approach achieves state-of-the-art performance against existing methods.
  arXiv  Detail & Related papers  (2023-12-05T18:54:03Z)
• Adversarial Score Distillation: When score distillation meets GAN [3.2794321281011394]
  We decipher existing score distillation with the Wasserstein Generative Adversarial Network (WGAN) paradigm. With the WGAN paradigm, we find that existing score distillation either employs a fixed sub-optimal discriminator or conducts incomplete discriminator optimization. We propose the Adversarial Score Distillation (ASD), which maintains an optimizable discriminator and updates it using the complete optimization objective.
  arXiv  Detail & Related papers  (2023-12-01T17:20:47Z)
• MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation Coefficient [11.48914285491747]
  Existing monocular 3D detection knowledge distillation methods usually project the LiDAR onto the image plane and train the teacher network accordingly. We propose MonoSKD, a novel Knowledge Distillation framework for Monocular 3D detection based on Spearman correlation coefficient. Our framework achieves state-of-the-art performance until submission with no additional inference computational cost.
  arXiv  Detail & Related papers  (2023-10-17T14:48:02Z)
• Diffusion-based 3D Object Detection with Random Boxes [58.43022365393569]
  Existing anchor-based 3D detection methods rely on empiricals setting of anchors, which makes the algorithms lack elegance. Our proposed Diff3Det migrates the diffusion model to proposal generation for 3D object detection by considering the detection boxes as generative targets. In the inference stage, the model progressively refines a set of random boxes to the prediction results.
  arXiv  Detail & Related papers  (2023-09-05T08:49:53Z)
• 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)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection [76.42897462051067]
  3DIoUMatch is a novel semi-supervised method for 3D object detection applicable to both indoor and outdoor scenes. We leverage a teacher-student mutual learning framework to propagate information from the labeled to the unlabeled train set in the form of pseudo-labels. Our method consistently improves state-of-the-art methods on both ScanNet and SUN-RGBD benchmarks by significant margins under all label ratios.
  arXiv  Detail & Related papers  (2020-12-08T11:06:26Z)

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.