השוואת שיטות

	Weakly supervised vision transformer	למידה מונחית-למחצה
תחום	למידה עמוקה	למידת מכונה
משפחה	Machine learning	Machine learning
שנת המקור	2021–2022	1970s–2006 (formalized)
הוגה השיטה	Dosovitskiy et al. (ViT); weak supervision paradigm from Zhou and others	Vapnik, V. N. and others (community of researchers, 1970s–2000s)
סוג	Self-attention image model with weakly supervised training	Learning paradigm
מקור מכונן	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
כינויים	WS-ViT, weakly supervised ViT, weak supervision with vision transformer, ViT with weak labels	SSL, semi-supervised machine learning, transductive learning, label-efficient learning
קשורות	4	5
תקציר	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.