EfficientNetV2 is a type convolutional neural network that has faster training speed and better parameter efficiency than previous models. To develop these models, the authors use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed. The models were searched from the search space enriched with new ops such as Fused-MBConv.
Architecturally the main differences are:
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Classification | 4 | 14.81% |
Activity Recognition | 2 | 7.41% |
Human Activity Recognition | 2 | 7.41% |
Image Classification | 2 | 7.41% |
Super-Resolution | 2 | 7.41% |
Adversarial Attack | 1 | 3.70% |
Edge-computing | 1 | 3.70% |
Federated Learning | 1 | 3.70% |
Language Modelling | 1 | 3.70% |