English
Related papers

Related papers: Evaluation Metrics for DNNs Compression

200 papers

Quantization is a widely used technique to compress and accelerate deep neural networks. However, conventional quantization methods use the same bit-width for all (or most of) the layers, which often suffer significant accuracy degradation…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Weihan Chen , Peisong Wang , Jian Cheng

Thanks to their state-of-the-art performance, deep neural networks are increasingly used for object recognition. To achieve these results, they use millions of parameters to be trained. However, when targeting embedded applications the size…

Machine Learning · Computer Science 2016-03-21 Guillaume Soulié , Vincent Gripon , Maëlys Robert

Efficient deep neural network (DNN) models equipped with compact operators (e.g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e.g., the total number of weights/operations) while maintaining a…

Machine Learning · Computer Science 2025-01-07 Yonggan Fu , Haichuan Yang , Jiayi Yuan , Meng Li , Cheng Wan , Raghuraman Krishnamoorthi , Vikas Chandra , Yingyan Celine Lin

For many applications it is critical to know the uncertainty of a neural network's predictions. While a variety of neural network parameter estimation methods have been proposed for uncertainty estimation, they have not been rigorously…

Machine Learning · Computer Science 2019-12-05 Nabeel Seedat , Christopher Kanan

This paper presents a new deep learning-based framework for robust nonlinear estimation and control using the concept of a Neural Contraction Metric (NCM). The NCM uses a deep long short-term memory recurrent neural network for a global…

Systems and Control · Electrical Eng. & Systems 2020-11-20 Hiroyasu Tsukamoto , Soon-Jo Chung

Deep neural networks generally involve some layers with mil- lions of parameters, making them difficult to be deployed and updated on devices with limited resources such as mobile phones and other smart embedded systems. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2016-08-29 Xing Wang , Jie Liang

There is a proliferation in the number of satellites launched each year, resulting in downlinking of terabytes of data each day. The data received by ground stations is often unprocessed, making this an expensive process considering the…

Computer Vision and Pattern Recognition · Computer Science 2021-07-09 Martina Lofqvist , José Cano

Lossy image compression is generally formulated as a joint rate-distortion optimization to learn encoder, quantizer, and decoder. However, the quantizer is non-differentiable, and discrete entropy estimation usually is required for rate…

Computer Vision and Pattern Recognition · Computer Science 2017-09-20 Mu Li , Wangmeng Zuo , Shuhang Gu , Debin Zhao , David Zhang

Deep neural networks (DNNs) have demonstrated their great potential in recent years, exceeding the per-formance of human experts in a wide range of applications. Due to their large sizes, however, compressiontechniques such as weight…

Computer Vision and Pattern Recognition · Computer Science 2021-10-15 Wentao Chen , Hailong Qiu , Jian Zhuang , Chutong Zhang , Yu Hu , Qing Lu , Tianchen Wang , Yiyu Shi , Meiping Huang , Xiaowe Xu

Security metrics present the security level of a system or a network in both qualitative and quantitative ways. In general, security metrics are used to assess the security level of a system and to achieve security goals. There are a lot of…

Cryptography and Security · Computer Science 2021-05-19 Simon Yusuf Enoch , Jin B. Hong , Mengmeng Ge , Dong Seong Kim

Deep Neural Networks have achieved remarkable success relying on the developing availability of GPUs and large-scale datasets with increasing network depth and width. However, due to the expensive computation and intensive memory,…

Machine Learning · Computer Science 2020-09-07 E Zhenqian , Gao Weiguo

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference, especially when deploying to edge or IoT devices with limited computation capacity and power consumption budget. The uniform bit…

Machine Learning · Computer Science 2020-04-27 Tao Wang , Junsong Wang , Chang Xu , Chao Xue

This paper performs a detailed, multi-faceted analysis of key challenges and common design caveats related to the development of efficient neural networks (NN) nonlinear channel equalizers in coherent optical communication systems. Our…

Signal Processing · Electrical Eng. & Systems 2022-06-01 Pedro J. Freire , Antonio Napoli , Bernhard Spinnler , Nelson Costa , Sergei K. Turitsyn , Jaroslaw E. Prilepsky

In recent years, convolutional neural networks (CNNs) took over the field of document analysis and they became the predominant model for word spotting. Especially attribute CNNs, which learn the mapping between a word image and an attribute…

Computer Vision and Pattern Recognition · Computer Science 2019-03-27 Fabian Wolf , Philipp Oberdiek , Gernot A. Fink

The rapid growth of digital data has heightened the demand for efficient lossless compression methods. However, existing algorithms exhibit trade-offs: some achieve high compression ratios, others excel in encoding or decoding speed, and…

Information Theory · Computer Science 2025-10-01 Md. Atiqur Rahman , MM Fazle Rabbi

This paper explores the combination of neural network quantization and entropy coding for memory footprint minimization. Edge deployment of quantized models is hampered by the harsh Pareto frontier of the accuracy-to-bitwidth tradeoff,…

Machine Learning · Computer Science 2024-06-11 C. Metz , O. Bichler , A. Dupret

Recent advances in neural networks have led to significant computational and memory demands, spurring interest in one-bit weight compression to enable efficient inference on resource-constrained devices. However, the theoretical…

Machine Learning · Computer Science 2025-10-21 Danil Akhtiamov , Reza Ghane , Babak Hassibi

This paper presents a method to explain how the information of each input variable is gradually discarded during the forward propagation in a deep neural network (DNN), which provides new perspectives to explain DNNs. We define two types of…

Machine Learning · Computer Science 2022-06-14 Haotian Ma , Hao Zhang , Fan Zhou , Yinqing Zhang , Quanshi Zhang

We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantized net is minimal.…

Machine Learning · Computer Science 2017-07-17 Miguel Á. Carreira-Perpiñán , Yerlan Idelbayev

Model compression is generally performed by using quantization, low-rank approximation or pruning, for which various algorithms have been researched in recent years. One fundamental question is: what types of compression work better for a…

Machine Learning · Computer Science 2021-07-12 Miguel Á. Carreira-Perpiñán , Yerlan Idelbayev