pith. sign in

arxiv: 1704.00648 · v2 · pith:5Z4AWVJTnew · submitted 2017-04-03 · 💻 cs.LG · cs.CV

Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations

Eirikur Agustsson , Fabian Mentzer , Michael Tschannen , Lukas Cavigelli , Radu Timofte , Luca Benini , Luc Van Gool This is my paper
classification 💻 cs.LG cs.CV
keywords quantizationapproachcompressiblecompressionend-to-endmethodrepresentationssoft-to-hard
0
0 comments X
read the original abstract

We present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy. Our method is based on a soft (continuous) relaxation of quantization and entropy, which we anneal to their discrete counterparts throughout training. We showcase this method for two challenging applications: Image compression and neural network compression. While these tasks have typically been approached with different methods, our soft-to-hard quantization approach gives results competitive with the state-of-the-art for both.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

    cs.CV 2022-08 unverdicted novelty 8.0

    Textual Inversion learns a single embedding vector from a few images to represent personal concepts inside the text embedding space of a frozen text-to-image model, enabling their composition in natural language prompts.

  2. Learning Image and Video Compression through Spatial-Temporal Energy Compaction

    eess.IV 2019-06 unverdicted novelty 5.0

    Learned image and video compression via autoencoders with spatial-temporal energy compaction penalties outperforms standards on MS-SSIM and visual quality.

  3. Deep Residual Learning for Image Compression

    eess.IV 2019-06 unverdicted novelty 3.0

    A learned image compression system using deep residual learning and sub-pixel convolution reaches 0.972 MS-SSIM at 0.15 bits per pixel in the CLIC validation phase.