English
Related papers

Related papers: Extreme Compression for Pre-trained Transformers M…

200 papers

There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural networks are often too resource-intensive in terms of energy and…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Yoshitomo Matsubara , Ruihan Yang , Marco Levorato , Stephan Mandt

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In…

Computation and Language · Computer Science 2019-08-27 Siqi Sun , Yu Cheng , Zhe Gan , Jingjing Liu

Over-fitting-based image compression requires weights compactness for compression and fast convergence for practical use, posing challenges for deep convolutional neural networks (CNNs) based methods. This paper presents a simple…

Image and Video Processing · Electrical Eng. & Systems 2023-10-13 Yun Ye , Yanjie Pan , Qually Jiang , Ming Lu , Xiaoran Fang , Beryl Xu

Transformer-based architectures have become the de-facto standard models for a wide range of Natural Language Processing tasks. However, their memory footprint and high latency are prohibitive for efficient deployment and inference on…

Machine Learning · Computer Science 2021-09-28 Yelysei Bondarenko , Markus Nagel , Tijmen Blankevoort

Deep convolutional neural networks (CNNs) are powerful tools for a wide range of vision tasks, but the enormous amount of memory and compute resources required by CNNs pose a challenge in deploying them on constrained devices. Existing…

Machine Learning · Computer Science 2019-10-30 Yiren Zhao , Xitong Gao , Daniel Bates , Robert Mullins , Cheng-Zhong Xu

Modern Neural Networks are eminent in achieving state of the art performance on tasks under Computer Vision, Natural Language Processing and related verticals. However, they are notorious for their voracious memory and compute appetite…

Computer Vision and Pattern Recognition · Computer Science 2020-12-18 Harshit Rampal , Aman Mohanty

As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high…

Computation and Language · Computer Science 2023-11-27 Nathan Brown , Ashton Williamson , Tahj Anderson , Logan Lawrence

While deep and large pre-trained models are the state-of-the-art for various natural language processing tasks, their huge size poses significant challenges for practical uses in resource constrained settings. Recent works in knowledge…

Computation and Language · Computer Science 2021-06-15 Subhabrata Mukherjee , Ahmed Hassan Awadallah , Jianfeng Gao

Fine-tuning transformer models after unsupervised pre-training reaches a very high performance on many different natural language processing tasks. Unfortunately, transformers suffer from long inference times which greatly increases costs…

Computation and Language · Computer Science 2022-03-30 David Peer , Sebastian Stabinger , Stefan Engl , Antonio Rodriguez-Sanchez

While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate conditions. To mitigate this, generative compression methods…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Chuqin Zhou , Xiaoyue Ling , Yunuo Chen , Jincheng Dai , Guo Lu , Wenjun Zhang

In the past few years, transformers have achieved promising performances on various computer vision tasks. Unfortunately, the immense inference overhead of most existing vision transformers withholds their from being deployed on edge…

Computer Vision and Pattern Recognition · Computer Science 2022-06-03 Zhiwei Hao , Jianyuan Guo , Ding Jia , Kai Han , Yehui Tang , Chao Zhang , Han Hu , Yunhe Wang

The emergence of accurate open large language models (LLMs) has led to a race towards performant quantization techniques which can enable their execution on end-user devices. In this paper, we revisit the problem of "extreme" LLM…

Machine Learning · Computer Science 2024-09-12 Vage Egiazarian , Andrei Panferov , Denis Kuznedelev , Elias Frantar , Artem Babenko , Dan Alistarh

Neural networks have shown great performance in cognitive tasks. When deploying network models on mobile devices with limited resources, weight quantization has been widely adopted. Binary quantization obtains the highest compression but…

Computer Vision and Pattern Recognition · Computer Science 2018-11-14 Hsin-Pai Cheng , Yuanjun Huang , Xuyang Guo , Yifei Huang , Feng Yan , Hai Li , Yiran Chen

Deep learning networks have achieved state-of-the-art accuracies on computer vision workloads like image classification and object detection. The performant systems, however, typically involve big models with numerous parameters. Once…

Machine Learning · Computer Science 2017-11-17 Asit Mishra , Debbie Marr

Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high. However, conventional fine-tuning suffers from the…

Machine Learning · Computer Science 2020-04-01 Tianhong Li , Jianguo Li , Zhuang Liu , Changshui Zhang

Convolution neural network demonstrates great capability for multiple tasks, such as image classification and many others. However, much resource is required to train a network. Hence much effort has been made to accelerate neural network…

Computer Vision and Pattern Recognition · Computer Science 2020-05-20 Fuyuan Lyu , Shien Zhu , Weichen Liu

Large language models (LLMs) can acquire strong code-generation capabilities through few-shot learning. In contrast, supervised fine-tuning is still needed for smaller models to achieve good performance. Such fine-tuning demands a large…

Computation and Language · Computer Science 2023-06-09 Zhangir Azerbayev , Ansong Ni , Hailey Schoelkopf , Dragomir Radev

Knowledge distillation has been proven to be effective in model acceleration and compression. It allows a small network to learn to generalize in the same way as a large network. Recent successes in pre-training suggest the effectiveness of…

Computation and Language · Computer Science 2021-07-20 Ye Lin , Yanyang Li , Ziyang Wang , Bei Li , Quan Du , Tong Xiao , Jingbo Zhu

Recent advances in generative compression methods have demonstrated remarkable progress in enhancing the perceptual quality of compressed data, especially in scenarios with low bitrates. However, their efficacy and applicability to achieve…

Computer Vision and Pattern Recognition · Computer Science 2023-12-18 Qi Mao , Tinghan Yang , Yinuo Zhang , Zijian Wang , Meng Wang , Shiqi Wang , Siwei Ma

Binarization is an extreme network compression approach that provides large computational speedups along with energy and memory savings, albeit at significant accuracy costs. We investigate the question of where to binarize inputs at…

Computer Vision and Pattern Recognition · Computer Science 2018-04-12 Ameya Prabhu , Vishal Batchu , Rohit Gajawada , Sri Aurobindo Munagala , Anoop Namboodiri