So sánh phương pháp

	Phát hiện đối tượng với ít mẫu	DETR (Detection Transformer)
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2020	2020
Người khởi xướng	Xin Wang	Nicolas Carion
Loại	Neural network architecture	Neural network architecture
Công trình gốc	Wang, X., Huang, T. E., Darrell, T., Gonzalez, J. E., & Yu, F. (2020). Few-shot object detection with attention-RPN and multi-relation detector. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9050-9059).	Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European Conference on Computer Vision (pp. 213-229). Springer, Cham.
Tên gọi khác	FSOD, Few-shot detection	Detection Transformer, DETR
Liên quan	3	4
Tóm tắt	Few-Shot Object Detection (FSOD) is a meta-learning approach that enables detecting novel object classes from only a few annotated examples. Unlike standard object detection requiring hundreds of labeled instances per class, FSOD learns to quickly adapt detection models to new object categories by leveraging knowledge from base categories.	DETR (Detection Transformer) is an end-to-end framework for object detection introduced by Carion et al. in 2020 that reformulates detection as a direct set prediction problem using transformers. Unlike traditional approaches that use hand-crafted post-processing like non-maximum suppression, DETR treats object detection as a sequence-to-sequence problem where the transformer predicts all objects at once.