PatchContrast: Self-Supervised Pre-training for 3D Object Detection
Accurately detecting objects in the environment is a key challenge for autonomous vehicles. However, obtaining annotated data for detection is expensive and time-consuming. We introduce PatchContrast, a novel self-supervised point cloud pre-training framework for 3D object detection. We propose to utilize two levels of abstraction to learn discriminative representation from unlabeled data: proposal-level and patch-level. The proposal-level aims at localizing objects in relation to their surroundings, whereas the patch-level adds information about the internal connections between the object's components, hence distinguishing between different objects based on their individual components. We demonstrate how these levels can be integrated into self-supervised pre-training for various backbones to enhance the downstream 3D detection task. We show that our method outperforms existing state-of-the-art models on three commonly-used 3D detection datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object DetectionAutonomous VehiclesObjectobject-detectionObject DetectionPoint Cloud Pre-trainingSimilar Papers 제목 키워드 기반
3D Object Detection with a Self-supervised Lidar Scene Flow Backbone
State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the …
3D Object DetectionObjectobject-detectionObject Detection+3A Survey of Self-Supervised and Few-Shot Object Detection
Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image. While few-shot object detection is about training a…
Few-Shot Object DetectionInstance SegmentationObjectobject-detection+3SeqCo-DETR: Sequence Consistency Training for Self-Supervised Object Detection with Transformers
Self-supervised pre-training and transformer-based networks have significantly improved the performance of object detection. However, most of the current self-supervised object detection methods are built on convolutiona…
Objectobject-detectionObject DetectionRepresentation LearningDETReg: Unsupervised Pretraining with Region Priors for Object Detection
Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-s…
Few-Shot LearningFew-Shot Object DetectionObjectobject-detection+5Sample, Crop, Track: Self-Supervised Mobile 3D Object Detection for Urban Driving LiDAR
Deep learning has led to great progress in the detection of mobile (i.e. movement-capable) objects in urban driving scenes in recent years. Supervised approaches typically require the annotation of large training sets; t…
3D Object DetectionObjectobject-detectionObject Detection+1