Dynamic Binary Neural Network by Learning Channel-Wise Thresholds

Zhang, Jiehua; Su, Zhuo; Feng, Yanghe; Lu, Xin; Pietikäinen, Matti; Liu, Li

doi:10.1109/icassp43922.2022.9747328

Cited by 14 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To boost feature expression capabilities, J. Zhang et al [90] replaced the static RSign and RPReLU in the ReActNet [87] with Dynamic Sign (DySign) and Dynamic PReLU (DyPReLU). Also, in [91], the authors proposed Binarized Ghost Module (BGM) as a modification for the ReActNet [87] to improve the feature maps information.…”

Section: C: Gradient Error Minimizationmentioning

confidence: 99%

A Systematic Literature Review on Binary Neural Networks

et al. 2023

View full text Add to dashboard Cite

This paper presents an extensive literature review on Binary Neural Network (BNN). BNN utilizes binary weights and activation function parameters to substitute the full-precision values. In digital implementations, BNN replaces the complex calculations of Convolutional Neural Networks (CNNs) with simple bitwise operations. BNN optimizes large computation and memory storage requirements, which leads to less area and power consumption compared to full-precision models. Although there are many advantages of BNN, the binarization process has a significant impact on the performance and accuracy of the generated models. To reflect the state-of-the-art in BNN and explore how to develop and improve BNNbased models, we conduct a systematic literature review on BNN with data extracted from 239 research studies. Our review discusses various BNN architectures and the optimization approaches developed to improve their performance. There are three main research directions in BNN: accuracy optimization, compression optimization, and acceleration optimization. The accuracy optimization approaches include quantization error reduction, special regularization, gradient error minimization, and network structure. The compression optimization approaches combine fractional BNN and pruning. The acceleration optimization approaches comprise computing in-memory, FPGA-based implementations, and ASIC-based implementations. At the end of our review, we present a comprehensive analysis of BNN applications and their evaluation metrics. Also, we shed some light on the most common BNN challenges and the future research trends of BNN.

show abstract

Section: C: Gradient Error Minimizationmentioning

confidence: 99%

A Systematic Literature Review on Binary Neural Networks

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Further innovation can be made to meet such inspiring target. For example, fusing PDC to binary neural networks [15,32,51]. -PDC enjoys the general form to organize the encoding of pixel differences, making it possible to incorporate any LBP variant to the convolutional module.…”

Section: Future Work and Conclusionmentioning

confidence: 99%

From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learning

Su¹,

Pietikäinen²,

Liu³

2023

Preprint

View full text Add to dashboard Cite

LBP is a successful hand-crafted feature descriptor in computer vision. However, in the deep learning era, deep neural networks, especially convolutional neural networks (CNNs) can automatically learn powerful task-aware features that are more discriminative and of higher representational capacity. To some extent, such hand-crafted features can be safely ignored when designing deep computer vision models. Nevertheless, due to LBP's preferable properties in visual representation learning, an interesting topic has arisen to explore the value of LBP in enhancing modern deep models in terms of efficiency, memory consumption, and predictive performance. In this paper, we provide a comprehensive review on such efforts which aims to incorporate the LBP mechanism into the design of CNN modules to make deep models stronger. In retrospect of what has been achieved so far, the paper discusses open challenges and directions for future research.

show abstract

“…Similarly, Bi-CPDC, Bi-APDC, and Bi-RPDC can be derived using different probing strategies. Generally, previous BCNNs [37,90,108] adopted a shared threshold τ over the whole image during binarization without considering local content variations, leading to the irreversible loss of high-order image details. As illustrated in Fig.…”

Section: Formulations Of Bi-pdcmentioning

confidence: 99%

Lightweight Pixel Difference Networks for Efficient Visual Representation Learning

Su,

Zhang,

Wang

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

Recently, there have been tremendous efforts in developing lightweight Deep Neural Networks (DNNs) with satisfactory accuracy, which can enable the ubiquitous deployment of DNNs in edge devices. The core challenge of developing compact and efficient DNNs lies in how to balance the competing goals of achieving high accuracy and high efficiency. In this paper we propose two novel types of convolutions, dubbed Pixel Difference Convolution (PDC) and Binary PDC (Bi-PDC) which enjoy the following benefits: capturing higher-order local differential information, computationally efficient, and able to be integrated with existing DNNs. With PDC and Bi-PDC, we further present two lightweight deep networks named Pixel Difference Networks (PiDiNet) and Binary PiDiNet (Bi-PiDiNet) respectively to learn highly efficient yet more accurate representations for visual tasks including edge detection and object recognition. Extensive experiments on popular datasets (BSDS500, ImageNet, LFW, YTF, etc.) show that PiDiNet and Bi-PiDiNet achieve the best accuracy-efficiency trade-off. For edge detection, PiDiNet is the first network that can be trained without ImageNet, and can achieve the human-level performance on BSDS500 at 100 FPS and with <1M parameters. For object recognition, among existing Binary DNNs, Bi-PiDiNet achieves the best accuracy and a nearly 2× reduction of computational cost on ResNet18.

show abstract

Dynamic Binary Neural Network by Learning Channel-Wise Thresholds

Cited by 14 publications

References 15 publications

A Systematic Literature Review on Binary Neural Networks

A Systematic Literature Review on Binary Neural Networks

From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learning

Lightweight Pixel Difference Networks for Efficient Visual Representation Learning

Contact Info

Product

Resources

About