Linganisha mbinu

	Kigeuzi cha Taswira Kinachosimamiwa Kidogo	Ujifunzaji Nusu-Simamiwa
Nyanja	Ujifunzaji wa Kina	Ujifunzaji wa Mashine
Familia	Machine learning	Machine learning
Mwaka wa asili	2021–2022	1970s–2006 (formalized)
Mwanzilishi	Dosovitskiy et al. (ViT); weak supervision paradigm from Zhou and others	Vapnik, V. N. and others (community of researchers, 1970s–2000s)
Aina	Self-attention image model with weakly supervised training	Learning paradigm
Chanzo asilia	Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (ICLR).	Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9
Majina mbadala	WS-ViT, weakly supervised ViT, weak supervision with vision transformer, ViT with weak labels	SSL, semi-supervised machine learning, transductive learning, label-efficient learning
Zinazohusiana	4	5
Muhtasari	Weakly Supervised Vision Transformer (WS-ViT) trains a Vision Transformer on image data that lacks precise pixel-level annotations, instead using cheaper, noisier supervision such as image-level class tags, bounding boxes, or web-scraped text. The global self-attention mechanism of the transformer makes it especially capable of localising objects and learning discriminative features from these incomplete labels.	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.