RI: Small: Deep Variational Data Compression

RI：小型：深度变分数据压缩

• 批准号: 2007719
• 负责人: Stephan Mandt
• 金额: $ 42.5万
• 依托单位: University of California-Irvine
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2007719&HistoricalAwards=false
• 关键词: RI; Small; Deep; Variational; Data

The internet and the world’s IT systems could not exist without data compression. From the efficient storage of large business databases to massive datasets collected by the Large Hadron Collider to video streaming—compression is a tool of fundamental importance that enables many of the systems our societies have come to depend on. It is estimated that by 2021, compressed video data alone will account for over 80% of internet traffic (an estimate made before COVID-19). Any gains that can be made in video coding efficiency will have a dramatic societal impact. Over the past few years, it has become clear that neural networks can significantly improve classical compression methods in terms of how they trade off data quality losses for file size. Besides this, neural compression methods also have other benefits: they can be fine-tuned to specific data modalities (e.g., medical images), do not show the common block-coding visual artifacts, and can be ‘supervised’ to allocate more attention to specific features of interest. This award contributes to better compression algorithms by improving video coding, enabling faster data transfer between machine learning systems, and improving the modularity of neural codec design, potentially impacting a wide range of applications.This project draws on deep latent variable modeling and promotes several new ideas for neural data compression: (i) hierarchical generative video coding; (ii) supervised compression, and (iii) plug and play compression of trained generative models. Part (i) proposes to combine normalizing flows with sequential variational autoencoders to predict future frames with higher confidence and shorter expected code lengths. Part (ii) leverages the ability of deep neural networks to be trained towards multiple tasks, such as data reconstruction and classification. Part (iii) describes a fundamentally new approach that decouples discretization from training, and that instead performs discretization and entropy coding jointly. The algorithm takes posterior uncertainties into account to allocate more bits to the features that are most important to reconstruct a given input data point while assigning fewer bits to features where some quantization error can be tolerated.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

没有数据压缩，互联网和世界的IT系统将不可能存在。从大型业务数据库的有效存储到大型强子对撞机收集的大量数据集，再到视频流 - 压缩是一种基本重要性的工具，可以使我们的社会许多系统都依赖。据估计，到2021年，仅压缩视频数据将占互联网流量的80％以上（Covid-19之前进行的估计）。视频编码效率中可以带来的任何收益都将产生巨大的社会影响。在过去的几年中，很明显，神经网络可以大大改善经典的压缩方法，以交换数据质量损失的文件大小。除此之外，神经元压缩方法还具有其他好处：它们可以对特定的数据模式（例如医学图像）进行微调，并未显示常见的块编码视觉伪像，并且可以“监督”以更多的关注对特定感兴趣的特征分配。该奖项通过改进视频编码，实现机器学习系统之间的更快数据传输以及改善神经元编解码器设计的模块化，有可能影响广泛的应用程序。该项目通过深层潜在可变建模并促进神经元数据压缩的几个新想法：（i（i）hierainical generartic Videmart tidemart iDEDERIDE; （ii）有监督的压缩，（iii）插入和播放受过训练的通用模型的压缩。 （i）部分提案将归一化流与顺序变异自动编码器结合起来，以更高的置信度和更短的预期代码长度来预测未来的帧。第（ii）部分利用了深层神经元网络对多个任务进行训练的能力，例如数据重建和分类。第（iii）部分描述了一种从根本上进行新的方法，该方法将离散化的培训与培训分解，并共同执行离散化和熵编码。该算法考虑了后部不确定性，以分配更多的位置，以对重建给定的输入数据点最重要的功能，同时将更少的位置分配给可以容忍一些量化错误的功能。该奖项反映了NSF的法定任务，并认为通过基金会的知识优点和广泛的criperia criperia criperia criperia criperia criptia the Issportiatuation the Conteruation the Priews通过评估来支持。

项目成果

Neural Transformation Learning for Deep Anomaly Detection Beyond Images

• 发表时间: 2021-03
• 期刊: ArXiv
• 作者: Chen Qiu;Timo Pfrommer;M. Kloft;S. Mandt;Maja R. Rudolph

Supervised Compression for Resource- constrained Edge Computing Systems

资源受限边缘计算系统的监督压缩

• DOI: 10.1109/wacv51458.2022.00100
• 发表时间: 2022
• 期刊: IEEE Winter Conference on Applications of Computer Vision (IEEE WACV
• 作者: Matsubara, Y;Yang, R.;Mandt, S;Levorato, M.
• 通讯作者: Levorato, M.

Hierarchical Autoregressive Modeling for Neural Video Compression

• 发表时间: 2020-10
• 期刊: ArXiv
• 作者: Ruihan Yang;Yibo Yang;Joseph Marino;S. Mandt

Scalable Gaussian Process Variational Autoencoders

• 发表时间: 2020-10
• 期刊: ArXiv
• 作者: Metod Jazbec;Vincent Fortuin;Michael Pearce;S. Mandt;Gunnar Rätsch

Towards Empirical Sandwich Bounds on the Rate-Distortion Function

• 发表时间: 2021-11
• 期刊: ArXiv
• 作者: Yibo Yang;S. Mandt