So sánh phương pháp

	Phân đoạn ngữ nghĩa yếu giám sát	Học bán giám sát
Lĩnh vực	Học sâu	Học máy
Họ	Machine learning	Machine learning
Năm ra đời	2014–2016	1970s–2006 (formalized)
Người khởi xướng	Multiple contributors; Class Activation Mapping (Zhou et al., 2016) is foundational	Vapnik, V. N. and others (community of researchers, 1970s–2000s)
Loại	Pixel-level classification with image-level or coarse supervision	Learning paradigm
Công trình gốc	Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning Deep Features for Discriminative Localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921–2929.	Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9
Tên gọi khác	WSSS, weak-label segmentation, image-level supervised segmentation, weakly-labeled pixel classification	SSL, semi-supervised machine learning, transductive learning, label-efficient learning
Liên quan	4	5
Tóm tắt	Weakly Supervised Semantic Segmentation (WSSS) trains pixel-level scene parsers using only cheap, coarse annotations — typically image-level class tags — instead of costly dense pixel masks. By generating proxy pseudo-labels from a classification network (via Class Activation Maps or similar localisation cues) and iteratively refining them, WSSS brings full-supervision accuracy within reach at a fraction of the annotation cost.	Semi-supervised learning (SSL) is a machine learning paradigm that trains models using a small set of labeled examples together with a much larger pool of unlabeled data. By leveraging the structure inherent in unlabeled data, SSL achieves accuracy closer to fully supervised models while requiring far fewer costly manual labels — making it practical when labeling is expensive, slow, or resource-constrained.