TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection

• URL: http://arxiv.org/abs/2409.10901v1
• Date: Tue, 17 Sep 2024 05:35:00 GMT
• Title: TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection
• Authors: Philip Jacobson, Yichen Xie, Mingyu Ding, Chenfeng Xu, Masayoshi Tomizuka, Wei Zhan, Ming C. Wu,
• Abstract summary: Pseudo-labeling approaches to semi-supervised learning adopt a teacher-student framework. We leverage pre-trained motion-forecasting models to generate object trajectories on pseudo-labeled data. Our approach improves pseudo-label quality in two distinct manners.
• Score: 59.498894868956306
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learning adopt a teacher-student framework in which machine-generated pseudo-labels on a large unlabeled dataset are used in combination with a small manually-labeled dataset for training. In this work, we address the problem of improving pseudo-label quality through leveraging long-term temporal information captured in driving scenes. More specifically, we leverage pre-trained motion-forecasting models to generate object trajectories on pseudo-labeled data to further enhance the student model training. Our approach improves pseudo-label quality in two distinct manners: first, we suppress false positive pseudo-labels through establishing consistency across multiple frames of motion forecasting outputs. Second, we compensate for false negative detections by directly inserting predicted object tracks into the pseudo-labeled scene. Experiments on the nuScenes dataset demonstrate the effectiveness of our approach, improving the performance of standard semi-supervised approaches in a variety of settings.

Related papers

• Dual-Perspective Knowledge Enrichment for Semi-Supervised 3D Object Detection [55.210991151015534]
  We present a novel Dual-Perspective Knowledge Enrichment approach named DPKE for semi-supervised 3D object detection. Our DPKE enriches the knowledge of limited training data, particularly unlabeled data, from two perspectives: data-perspective and feature-perspective.
  arXiv  Detail & Related papers  (2024-01-10T08:56:07Z)
• LabelFormer: Object Trajectory Refinement for Offboard Perception from LiDAR Point Clouds [37.87496475959941]
  "Auto-labelling" offboard perception models are trained to automatically generate annotations from raw LiDAR point clouds. We propose LabelFormer, a simple, efficient, and effective trajectory-level refinement approach. Our approach first encodes each frame's observations separately, then exploits self-attention to reason about the trajectory with full temporal context.
  arXiv  Detail & Related papers  (2023-11-02T17:56:06Z)
• Doubly Robust Self-Training [46.168395767948965]
  We introduce doubly robust self-training, a novel semi-supervised algorithm. We demonstrate the superiority of the doubly robust loss over the standard self-training baseline.
  arXiv  Detail & Related papers  (2023-06-01T00:57:16Z)
• Semi-supervised 3D Object Detection with Proficient Teachers [114.54835359657707]
  Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples. Pseudo-Labeling methodology is commonly used for SSL frameworks, however, the low-quality predictions from the teacher model have seriously limited its performance. We propose a new Pseudo-Labeling framework for semi-supervised 3D object detection, by enhancing the teacher model to a proficient one with several necessary designs.
  arXiv  Detail & Related papers  (2022-07-26T04:54:03Z)
• PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems [42.51709009844805]
  We propose a new approach to generate robust pseudo-labels by leveraging motion continuity in video frames. Our method outperforms the state-of-the-art semi-supervised object detection methods by 7.4% on mAP75.
  arXiv  Detail & Related papers  (2022-03-11T15:09:29Z)
• Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection [85.11649974840758]
  3D object detection networks tend to be biased towards the data they are trained on. We propose a single-frame approach for source-free, unsupervised domain adaptation of lidar-based 3D object detectors.
  arXiv  Detail & Related papers  (2021-11-30T18:42:42Z)
• Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation [90.2445084743881]
  We present a method for semi-supervised point cloud semantic segmentation to adopt unlabeled point clouds in training to boost the model performance. Inspired by the recent contrastive loss in self-supervised tasks, we propose the guided point contrastive loss to enhance the feature representation and model generalization ability.
  arXiv  Detail & Related papers  (2021-10-15T16:38:54Z)
• ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection [78.71826145162092]
  We present a self-training method, named ST3D++, with a holistic pseudo label denoising pipeline for unsupervised domain adaptation on 3D object detection. We equip the pseudo label generation process with a hybrid quality-aware triplet memory to improve the quality and stability of generated pseudo labels. In the model training stage, we propose a source data assisted training strategy and a curriculum data augmentation policy.
  arXiv  Detail & Related papers  (2021-08-15T07:49:06Z)

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.