paper-with-me

홈 › Papers

Probabilistic Connection Importance Inference and Lossless Compression of Deep Neural Networks

2020-05-01 · ICLR 2020 1 · Xin Xing, Long Sha, Pengyu Hong, Zuofeng Shang, Jun S. Liu

Deep neural networks (DNNs) can be huge in size, requiring a considerable a mount of energy and computational resources to operate, which limits their applications in numerous scenarios. It is thus of interest to compress DNNs while maintaining their performance levels. We here propose a probabilistic importance inference approach for pruning DNNs. Specifically, we test the significance of the relevance of a connection in a DNN to the DNN’s outputs using a nonparemtric scoring testand keep only those significant ones. Experimental results show that the proposed approach achieves better lossless compression rates than existing techniques

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Importance weighted compression

2021-03-04 · ICLR Workshop Neural_Compression 2021 5 · Lucas Theis, Jonathan Ho

The connection between variational autoencoders (VAEs) and compression is well established and they have been used for both lossless and lossy compression. Compared to VAEs, importance-weighted autoencoders (IWAEs) achie…

Generalization Gap in Amortized Inference

2022-05-23 · Mingtian Zhang, Peter Hayes, David Barber

The ability of likelihood-based probabilistic models to generalize to unseen data is central to many machine learning applications such as lossless compression. In this work, we study the generalization of a popular clas…

HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models

2019-12-20 · ICLR 2020 1 · James Townsend, Thomas Bird, Julius Kunze, David Barber

We make the following striking observation: fully convolutional VAE models trained on 32x32 ImageNet can generalize well, not just to 64x64 but also to far larger photographs, with no changes to the model. We use this pr…

Image Compression

Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression

2022-09-11 · Yuanchao Bai, Xianming Liu, Kai Wang, Xiangyang Ji 외

Lossless and near-lossless image compression is of paramount importance to professional users in many technical fields, such as medicine, remote sensing, precision engineering and scientific research. But despite rapidly…

Image Compression

Learning Better Lossless Compression Using Lossy Compression

2020-03-23 · CVPR 2020 6 · Fabian Mentzer, Luc van Gool, Michael Tschannen

We leverage the powerful lossy image compression algorithm BPG to build a lossless image compression system. Specifically, the original image is first decomposed into the lossy reconstruction obtained after compressing i…

Image Compression