Permute, Quantize, and Fine-Tune: Efficient Compression of Neural Networks.
Julieta MartinezJashan ShewakramaniTing-Wei LiuIoan Andrei BarsanWenyuan ZengRaquel UrtasunPublished in: CVPR (2021)
Keyphrases
- fine tune
- neural network
- efficient compression
- fine tuning
- bit rate
- higher quality
- image compression
- fault diagnosis
- artificial neural networks
- fuzzy logic
- back propagation
- video codec
- video compression
- genetic algorithm
- fuzzy systems
- motion compensated
- inter frame
- pid controller
- low bit rate
- neural network model
- video coding
- optimization algorithm
- multiresolution