paper-with-me

Papers

Ternary and Binary Quantization for Improved Classification

2022-03-31 · Weizhi Lu, Mingrui Chen, Kai Guo, Weiyu Li

Dimension reduction and data quantization are two important methods for reducing data complexity. In the paper, we study the methodology of first reducing data dimension by random projection and then quantizing the projections to ternary or binary codes, which has been widely applied in classification. Usually, the quantization will seriously degrade the accuracy of classification due to high quantization errors. Interestingly, however, we observe that the quantization could provide comparable and often superior accuracy, as the data to be quantized are sparse features generated with common filters. Furthermore, this quantization property could be maintained in the random projections of sparse features, if both the features and random projection matrices are sufficiently sparse. By conducting extensive experiments, we validate and analyze this intriguing property.

📄 PDF Abstract BibTeX arXiv:2203.16798

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationDimensionality ReductionQuantization

Similar Papers 제목 키워드 기반

Smart Ternary Quantization

2019-09-25 · Gregoire Morin, Ryan Razani, Vahid Partovi Nia, Eyyub Sari

Neural network models are resource hungry. Low bit quantization such as binary and ternary quantization is a common approach to alleviate this resource requirements. Ternary quantization provides a more flexible model an…

image-classificationImage ClassificationQuantization

The Binary and Ternary Quantization Can Improve Feature Discrimination

2025-04-18 · Weizhi Lu, Mingrui Chen, Weiyu Li

In machine learning, quantization is widely used to simplify data representation and facilitate algorithm deployment on hardware. Given the fundamental role of classification in machine learning, it is crucial to investi…

ClassificationQuantization

Adaptive Binary-Ternary Quantization

2019-09-26 · Ryan Razani, Grégoire Morin, Vahid Partovi Nia, Eyyüb Sari

Neural network models are resource hungry. It is difficult to deploy such deep networks on devices with limited resources, like smart wearables, cellphones, drones, and autonomous vehicles. Low bit quantization such as b…

Autonomous VehiclesImage ClassificationQuantization

BinaryBERT: Pushing the Limit of BERT Quantization

2020-12-31 · ACL 2021 5 · Haoli Bai, Wei zhang, Lu Hou, Lifeng Shang 외

The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pu…

BinarizationModel CompressionQuantization

Ternary Quantization: A Survey

2023-03-02 · Dan Liu, Xue Liu

Inference time, model size, and accuracy are critical for deploying deep neural network models. Numerous research efforts have been made to compress neural network models with faster inference and higher accuracy. Prunin…

QuantizationSurvey