Linganisha mbinu

	Kigeuzi cha Taswira Kinachosimamiwa Kidogo	Ufumbuzi wa Maarifa
Nyanja	Ujifunzaji wa Kina	Ujifunzaji wa Kina
Familia	Machine learning	Machine learning
Mwaka wa asili	2021–2022	2015
Mwanzilishi	Dosovitskiy et al. (ViT); weak supervision paradigm from Zhou and others	Hinton, G., Vinyals, O. & Dean, J.
Aina	Self-attention image model with weakly supervised training	Neural network compression (teacher–student)
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).	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.
Majina mbadala	WS-ViT, weakly supervised ViT, weak supervision with vision transformer, ViT with weak labels	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation
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.	Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster.