Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networks.
Julieta MartinezJashan ShewakramaniTing-Wei LiuIoan Andrei BârsanWenyuan ZengRaquel UrtasunPublished in: CoRR (2020)
Keyphrases
- fine tune
- neural network
- efficient compression
- higher quality
- fine tuning
- bit rate
- image compression
- artificial neural networks
- video compression
- genetic algorithm
- back propagation
- video coding
- fuzzy logic
- video codec
- visual quality
- neural network model
- real time
- image processing
- motion compensation
- rate distortion
- fault diagnosis
- post processing
- image data