A Category-Agnostic Hybrid Contrastive Learning Method for Few-Shot Point Cloud Object Detection
Source abstract
Abstract
Few-shot point cloud 3D object detection (FS3D) aims to identify and locate objects of novel classes within point clouds using knowledge acquired from annotated base classes and a minimal number of samples from the novel clas... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Optical Systems and Laser Technology · Remote Sensing and LiDAR Applications · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (28)
Show source-provided references
1. Rukhovich D, Vorontsova A, Konushin A. TR3D: towards real-time indoor 3D object detection. arXiv:230202858. 2023.10.1109/ICIP49359.2023.10222644 ↗
2. Shen Y, Geng Z, Yuan Y, Lin Y, Liu Z, Wang C, et al. V-DETR: DETR with vertex relative position encoding for 3D object detection. arXiv:230804409. 2023.
3. Yang H, Shi C, Chen Y, Wang L. Boosting 3D object detection via object-focused image fusion. arXiv:220710589. 2022.
4. Multi-head attention graph network for few shot learning
5. TabLLM: few-shot classification of tabular data with large language models
6. Revisiting logistic-softmax likelihood in bayesian meta-learning for few-shot classification
7. MIANet: aggregating unbiased instance and general information for few-shot semantic segmentation
8. Part-whole relational few-shot 3D point cloud semantic segmentation
9. Learning orthogonal prototypes for generalized few-shot semantic segmentation
10. Few-shot object detection with attention-RPN and multi-relation detector
11. Few-shot object detection based on the transformer and high-resolution network
12. Multi-faceted distillation of base-novel commonality for few-shot object detection
13. Few-shot object detection with fully cross-transformer
14. Prototypical votenet for few-shot 3D point cloud object detection
15. Meta-Det3D: learn to learn few-shot 3D object detection
16. Liu J, Dong X, Zhao S, Shen J. Generalized few-shot 3D object detection of LiDAR point cloud for autonomous driving. arXiv:230203914. 2023.
17. Prototypical variational autoencoder for 3D few-shot object detection
18. A simple framework for contrastive learning of visual representations
19. Few-shot classification with contrastive learning
20. Spatial contrastive learning for few-shot classification
21. Learning a few-shot embedding model with contrastive learning
22. Contrastive boundary learning for point cloud segmentation
23. Contextrast: contextual contrastive learning for semantic segmentation
24. Pointnet++: deep hierarchical feature learning on point sets in a metric space
25. Deep hough voting for 3D object detection in point clouds
26. Self-supervised learning for few-shot image classification
27. Scannet: richly-annotated 3d reconstructions of indoor scenes
28. Sun RGB-D: a RGB-D scene understanding benchmark suite