So sánh phương pháp

	Phát hiện đối tượng yếu giám sát	Phát hiện đối tượng bán giám sát
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2016 (deep WSOD); MIL roots circa 1997	2020–2021
Người khởi xướng	Bilen, H. & Vedaldi, A. (WSDDN); Multiple Instance Learning origins: Dietterich et al. (1997)	Sohn et al. (STAC); Liu et al. (Unbiased Teacher)
Loại	Weakly supervised detection paradigm	Semi-supervised learning for detection
Công trình gốc	Bilen, H., & Vedaldi, A. (2016). Weakly supervised deep detection networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2846–2854.	Sohn, K., Zhang, Z., Li, C.-L., Zhang, H., Lee, C.-Y., & Pfister, T. (2020). A Simple Semi-Supervised Learning Framework for Object Detection. arXiv preprint arXiv:2005.04757.
Tên gọi khác	WSOD, weakly-supervised detection, image-level supervised detection, multiple instance detection	SSOD, semi-supervised detection, pseudo-label object detection, label-efficient object detection
Liên quan	5	6
Tóm tắt	Weakly Supervised Object Detection (WSOD) trains object detectors using only image-level labels — indicating which object classes appear in an image — without requiring costly bounding-box annotations. Multiple Instance Learning (MIL) formulations allow the model to discover the likely location of each object class from classification signals alone, dramatically reducing annotation cost.	Semi-supervised object detection trains a detector on a small labeled image set and a large unlabeled image set. A teacher model generates pseudo-labels for unlabeled images, and a student model learns from both real and pseudo-labeled data, dramatically reducing the expensive manual bounding-box annotation burden while achieving accuracy competitive with fully supervised baselines.