The student-t mixture as a natural image patch prior with application to image compression
By Aäron van den Oord, Benjamin Schrauwen. 2014
42 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Probabilistic & Bayesian Methods
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yoshua Bengio
- Kyunghyun Cho
- Quoc V. Le
- Mohit Bansal
- Sergey Levine
- Ruslan Salakhutdinov
- Jianfeng Gao
- Richard Socher
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Trevor Darrell
- Xiaogang Wang
- Jitendra Malik
- Andrea Vedaldi
- Andrew Zisserman
In Probabilistic & Bayesian Methods
- Lucas Theis
- Matthias Bethge
- Aäron van den Oord
- Koray Kavukcuoglu
- Yarin Gal
- Ferenc Huszár
- Oriol Vinyals
- Nal Kalchbrenner
Citations in the corpus
- Pixel Recurrent Neural Networks (2016, background): “These numbers are interpretable as the number of bits that a compression scheme based on this model would need to compress every RGB color value (van den Oord & Schrauwen, 2014b; Theis et al., 2015); in practice there is also a small overhead due to arithmetic coding.”
- Conditional Image Generation with PixelCNN Decoders (2016, background): “…as providing excellent samples, this network has the advantage of returning explicit probability densities (unlike alternatives such as generative adversarial networks [6, 3, 19]), making it straightforward to apply in domains such as compression [32] and probabilistic planning and exploration [2].”
- Generative Image Modeling Using Spatial LSTMs (2015, background): “We find that already an MCGSM (with 128 components and 48 quadratic features) outperforms all single models including a deep Gaussian mixture model [46] (Table 1).”
- Lossy Image Compression with Compressive Autoencoders (2017, positive): “While other trained algorithms have been shown to provide similar results as JPEG 2000 (e.g. van den Oord & Schrauwen, 2014), to our knowledge this is the first time that an end-to-end trained architecture has been demonstrated to achieve this level of performance on high-resolution images.”
- Factoring Variations in Natural Images with Deep Gaussian Mixture Models (2014, background): “Of course, the disadvantage of these mixture models is that they have less representational power than deep models.”