Hierarchical Quantized Autoencoders - Papers With Code

• Browse State-of-the-Art
• Datasets
• Methods
• More Newsletter RC2022 About Trends Portals Libraries

• Sign In

Subscribe to the PwC Newsletter

× Stay informed on the latest trending ML papers with code, research developments, libraries, methods, and datasets. Read previous issues Subscribe

Join the community

× You need to log in to edit. You can create a new account if you don't have one.

Edit Social Preview

× Description Default Custom Implemented in one code library. Image Default Custom None File is too large

Upload an image to customize your repository’s social media preview. Images should be at least 640×320px (1280×640px for best display).

Close Save

Add a new code entry for this paper

× GitHub, GitLab or BitBucket URL:* Official code from paper authors Submit

Remove a code repository from this paper

× speechmatics/hqa 37 -

Mark the official implementation from paper authors

× speechmatics/hqa 37 There is no official implementation Multiple official implementations Submit

Add a new evaluation result row

× Task:* --------- Quantization Image Compression Not in the list? Add a task. Dataset:* --------- Model name:* Metric name:* --------- Higher is better (for the metric) Metric value:* Uses extra training data Data evaluated on Submit

Add a new evaluation result row

×

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE

Add a task

× Attached tasks:

• IMAGE COMPRESSION

• QUANTIZATION

Add: --------- Not in the list? Create a new task. New task name: Top-level area: --------- Adversarial Audio Computer Code Computer Vision Graphs Knowledge Base Medical Methodology Miscellaneous Music Natural Language Processing Playing Games Reasoning Robots Speech Time Series Parent task (if any): --------- Description: Submit

Remove a task

×

• Image Compression -

• Quantization -

Add a method

× Attached methods:

• VQ-VAE

Add: --------- Not in the list? Create a new method. New method name (e.g. ReLU): New method full name (e.g. Rectified Linear Unit): Paper where method was first introduced: --------- Method category (e.g. Activation Functions): If no match, add something for now then you can add a new category afterwards. --------- Markdown description (optional; $\LaTeX$ enabled): You can edit this later, so feel free to start with something succinct. Submit

Remove a method

×

• VQ-VAE -

Edit Datasets

× Add or remove datasets introduced in this paper: Add or remove other datasets used in this paper: CelebA Paper introduces a new dataset? Add a new dataset here Save Hierarchical Quantized Autoencoders

NeurIPS 2020 · Will Williams, Sam Ringer, Tom Ash, John Hughes, David MacLeod, Jamie Dougherty · Edit social preview

Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and abstract features at very low bitrates. Encouraged by recent success in learning discrete representations with Vector Quantized Variational Autoencoders (VQ-VAEs), we motivate the use of a hierarchy of VQ-VAEs to attain high factors of compression. We show that the combination of stochastic quantization and hierarchical latent structure aids likelihood-based image compression. This leads us to introduce a novel objective for training hierarchical VQ-VAEs. Our resulting scheme produces a Markovian series of latent variables that reconstruct images of high-perceptual quality which retain semantically meaningful features. We provide qualitative and quantitative evaluations on the CelebA and MNIST datasets.

PDF Abstract NeurIPS 2020 PDF NeurIPS 2020 Abstract

Code Edit Add Remove Mark official

speechmatics/hqa 37 speechmatics/hqa 37

Tasks Edit Add Remove

Image Compression Quantization

Datasets Edit

CelebA

Results from the Paper Edit Add Remove

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods Edit Add Remove

VQ-VAE Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA. Terms Data policy Cookies policy from