เปรียบเทียบวิธี

	วิทัศน์ทรานส์ฟอร์มแบบมีผู้สอนแบบอ่อน	การกลั่นความรู้
สาขาวิชา	การเรียนรู้เชิงลึก	การเรียนรู้เชิงลึก
ตระกูล	Machine learning	Machine learning
ปีกำเนิด	2021–2022	2015
ผู้ริเริ่ม	Dosovitskiy et al. (ViT); weak supervision paradigm from Zhou and others	Hinton, G., Vinyals, O. & Dean, J.
ประเภท	Self-attention image model with weakly supervised training	Neural network compression (teacher–student)
แหล่งต้นตำรับ	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.
ชื่อเรียกอื่น	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
ที่เกี่ยวข้อง	4	5
สรุป	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.