השוואת שיטות

	זיקוק ידע (Knowledge Distillation)	למידה ויזואלית ניגודית
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2015	2020
הוגה השיטה	Hinton, G., Vinyals, O. & Dean, J.	Chen, T. et al. (SimCLR); He, K. et al. (MoCo)
סוג	Neural network compression (teacher–student)	Self-supervised deep representation learning
מקור מכונן	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. ICML.
כינויים	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	Karşıtlık Öğrenmesi — Görsel (SimCLR / MoCo / BYOL), contrastive learning, self-supervised visual representation learning, SimCLR
קשורות	5	5
תקציר	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.	Visual contrastive learning is a self-supervised deep-learning approach — popularised by frameworks such as SimCLR (Chen et al., 2020) and MoCo (He et al., 2020) — that learns rich image representations without labels by pulling different augmentations of the same image together and pushing different images apart. It turns a large pool of unlabelled images into a useful feature extractor.