Soft-to-Hard Vector Quantization for End-to-End Learned Compression of Images and Neural Networks
By Eirikur Agustsson, Fabian Mentzer, Michael Tschannen, Lukas Cavigelli, Radu Timofte, Luca Benini, Luc Van Gool. 2017
46 citations recorded by the source corpus.
Subfields: Generative Models, Efficiency & Compression
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Generative Models
- Daniel Cohen-Or
- Aäron van den Oord
- Rinon Gal
- Oriol Vinyals
- Yuval Alaluf
- Amit H. Bermano
- Or Patashnik
- Neil Zeghidour
In Efficiency & Compression
- Aäron van den Oord
- Gal Chechik
- Koray Kavukcuoglu
- Oriol Vinyals
- Olivier Pietquin
- Marco Tagliasacchi
- David Grangier
- Dominik Roblek
Citations in the corpus
- Neural Discrete Representation Learning (2017, methodology): “Other authors [1] propose a method for similar compression model with vector quantisation.”
- AudioLM: A Language Modeling Approach to Audio Generation (2022, background): “Moreover, combining such high-quality synthesis systems with differentiable quantization [22], [23], [24],”
- Low Bit-rate Speech Coding with VQ-VAE and a WaveNet Decoder (2019, background): “These models are able to learn the redundancies in signals directly by being exposed to many examples during training, and have been successfully applied in the domain of image compression [1–4].”
- End-To-End Optimized Speech Coding with Deep Neural Networks (2017, neutral): “[14].”
- An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion (2022, methodology): “An encoder E learns to map images x ∈ D x into a spatial latent code z = E ( x ) , regularized through either a KL-divergence loss or through vector quantization (Van Den Oord et al., 2017; Agustsson et al., 2017).”