ScholarGate
Assistent

Jämför metoder

Granska de valda metoderna sida vid sida; rader som skiljer sig är markerade.

EfficientNet×Kunskapsdestillering×
ÄmnesområdeDjupinlärningDjupinlärning
FamiljMachine learningMachine learning
Ursprungsår20192015
UpphovspersonTan, M. & Le, Q. V.Hinton, G., Vinyals, O. & Dean, J.
TypCompound-scaled convolutional neural network architectureNeural network compression (teacher–student)
UrsprungskällaTan, M. & Le, Q. V. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning (ICML 2019), PMLR 97, 6105–6114. link ↗Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗
AliasEfficientNet, compound scaling CNN, EfficientNet-B0 through B7, EfficientNetV2Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation
Närliggande45
SammanfattningEfficientNet is a family of convolutional neural network architectures introduced by Mingxing Tan and Quoc V. Le (Google Brain) at ICML 2019 that systematically co-scales network depth, width, and input resolution using a single compound coefficient, achieving state-of-the-art image classification accuracy with substantially fewer parameters and FLOPs than prior networks such as ResNet and Inception.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.
ScholarGateDatamängd
  1. v1
  2. 2 Källor
  3. PUBLISHED
  1. v1
  2. 2 Källor
  3. PUBLISHED

Gå till sökningen Ladda ner bildspel

ScholarGateJämför metoder: EfficientNet · Knowledge Distillation. Hämtad 2026-06-18 från https://scholargate.app/sv/compare