English
Related papers

Related papers: And the Bit Goes Down: Revisiting the Quantization…

200 papers

In deep learning frameworks, weight pruning is a widely used technique for improving computational efficiency by reducing the size of large models. This is especially critical for convolutional operators, which often act as performance…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-24 Chi-Wei Chu , Ding-Yong Hong , Jan-Jan Wu

Lossy image compression algorithms are pervasively used to reduce the size of images transmitted over the web and recorded on data storage media. However, we pay for their high compression rate with visual artifacts degrading the user…

Computer Vision and Pattern Recognition · Computer Science 2018-01-30 Lukas Cavigelli , Pascal Hager , Luca Benini

Recently, deep learning has become a de facto standard in machine learning with convolutional neural networks (CNNs) demonstrating spectacular success on a wide variety of tasks. However, CNNs are typically very demanding computationally at…

Computer Vision and Pattern Recognition · Computer Science 2019-09-27 Yochai Zur , Chaim Baskin , Evgenii Zheltonozhskii , Brian Chmiel , Itay Evron , Alex M. Bronstein , Avi Mendelson

The amount of data processed in the cloud, the development of Internet-of-Things (IoT) applications, and growing data privacy concerns force the transition from cloud-based to edge-based processing. Limited energy and computational…

Hardware Architecture · Computer Science 2023-08-02 Olga Krestinskaya , Li Zhang , Khaled Nabil Salama

By quantizing network weights and activations to low bitwidth, we can obtain hardware-friendly and energy-efficient networks. However, existing quantization techniques utilizing the straight-through estimator and piecewise constant…

Machine Learning · Computer Science 2024-07-24 Hiroyuki Tokunaga , Joel Nicholls , Daria Vazhenina , Atsunori Kanemura

Convolutional Neural Networks (CNNs) has shown a great success in many areas including complex image classification tasks. However, they need a lot of memory and computational cost, which hinders them from running in relatively low-end…

Machine Learning · Computer Science 2017-01-26 Marcella Astrid , Seung-Ik Lee

With the development of deep neural networks, the size of network models becomes larger and larger. Model compression has become an urgent need for deploying these network models to mobile or embedded devices. Model quantization is a…

Machine Learning · Computer Science 2019-07-02 Wen-Pu Cai , Wu-Jun Li

Quantization is a popular way of increasing the speed and lowering the memory usage of Convolution Neural Networks (CNNs). When labelled training data is available, network weights and activations have successfully been quantized down to…

Computer Vision and Pattern Recognition · Computer Science 2019-11-11 Marcelo Gennari , Roger Fawcett , Victor Adrian Prisacariu

Convolutional neural networks (CNNs) have made significant advances in computer vision tasks, yet their high inference times and latency often limit real-world applicability. While model compression techniques have gained popularity as…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Zhumazhan Balapanov , Vanessa Matvei , Olivia Holmberg , Edward Magongo , Jonathan Pei , Kevin Zhu

Recent work in network quantization has substantially reduced the time and space complexity of neural network inference, enabling their deployment on embedded and mobile devices with limited computational and memory resources. However,…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Bichen Wu , Yanghan Wang , Peizhao Zhang , Yuandong Tian , Peter Vajda , Kurt Keutzer

Tensor decomposition is one of the fundamental technique for model compression of deep convolution neural networks owing to its ability to reveal the latent relations among complex structures. However, most existing methods compress the…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Bo-Shiuan Chu , Che-Rung Lee

Model compression is instrumental in optimizing deep neural network inference on resource-constrained hardware. The prevailing methods for network compression, namely quantization and pruning, have been shown to enhance efficiency at the…

Machine Learning · Computer Science 2023-06-13 Ben Zandonati , Glenn Bucagu , Adrian Alan Pol , Maurizio Pierini , Olya Sirkin , Tal Kopetz

The increasing size of recently proposed Neural Networks makes it hard to implement them on embedded devices, where memory, battery and computational power are a non-trivial bottleneck. For this reason during the last years network…

Machine Learning · Computer Science 2025-09-30 Dalila Ressi , Riccardo Romanello , Sabina Rossi , Carla Piazza

Transformers are the backbone of powerful foundation models for many Vision and Natural Language Processing tasks. But their compute and memory/storage footprint is large, and so, serving such models is expensive often requiring high-end…

Machine Learning · Computer Science 2024-08-01 Harshavardhan Adepu , Zhanpeng Zeng , Li Zhang , Vikas Singh

Neural network quantization methods often involve simulating the quantization process during training, making the trained model highly dependent on the target bit-width and precise way quantization is performed. Robust quantization offers…

Machine Learning · Computer Science 2020-10-23 Moran Shkolnik , Brian Chmiel , Ron Banner , Gil Shomron , Yury Nahshan , Alex Bronstein , Uri Weiser

Convolution Neural Networks (CNN) have been extremely successful in solving intensive computer vision tasks. The convolutional filters used in CNNs have played a major role in this success, by extracting useful features from the inputs.…

Computer Vision and Pattern Recognition · Computer Science 2020-01-08 Pravendra Singh , Pratik Mazumder , Vinay P. Namboodiri

While deep neural networks are a highly successful model class, their large memory footprint puts considerable strain on energy consumption, communication bandwidth, and storage requirements. Consequently, model size reduction has become an…

Machine Learning · Statistics 2018-10-02 Marton Havasi , Robert Peharz , José Miguel Hernández-Lobato

To deploy deep neural networks on resource-limited devices, quantization has been widely explored. In this work, we study the extremely low-bit networks which have tremendous speed-up, memory saving with quantized activation and weights. We…

Machine Learning · Computer Science 2019-12-16 Yuhang Li , Xin Dong , Sai Qian Zhang , Haoli Bai , Yuanpeng Chen , Wei Wang

We study the problem of compressing recurrent neural networks (RNNs). In particular, we focus on the compression of RNN acoustic models, which are motivated by the goal of building compact and accurate speech recognition systems which can…

Computation and Language · Computer Science 2016-05-03 Rohit Prabhavalkar , Ouais Alsharif , Antoine Bruguier , Ian McGraw

Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. While aggressive quantization (i.e., less than 4-bits) performs…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Shahaf E. Finder , Yair Zohav , Maor Ashkenazi , Eran Treister