23 papers · ranked by Valyu relevance
Reza Nasirigerdeh, Reihaneh Torkzadehmahani, Daniel Rueckert, Georgios Kaissis
'Georgios Kaissis'] Existing convolutional neural network architectures frequently rely upon batch normalization (BatchNorm) to effectively train the model. BatchNorm, however, performs poorly with small batch sizes, and is inapplicable to differential privacy. To address these limitations, we propose the kernel…
Jungwoo Shin, HyunJin Kim, Yilun Shang
In this study, we present a novel performance-enhancing binarized neural network model called PresB-Net: Parametric Binarized Neural Network. A binarized neural network (BNN) model can achieve fast output computation with low hardware costs by using binarized weights and features. However, performance degradation is…
Gustavo Pérez, Stella X. Yu
Classical image filters, such as those for averaging or differencing, are carefully normalized to ensure consistency, interpretability, and to avoid artifacts like intensity shifts, halos, or ringing. In contrast, convolutional filters learned end-to-end in deep networks lack such constraints. Although they may…
Dayananda Pruthviraja, Ujjwal Mohan Kumar, Sunil Parameswaran, Vemulapalli Guna Chowdary + 2 more
'Vemulapalli Guna Chowdary' 'Varun Bharadwaj' 'Jyotismita Chaki'] Facial emotion detection is crucial in affective computing, with applications in human-computer interaction, psychological research, and sentiment analysis. This study explores how deep convolutional neural networks (DCNNs) can enhance the accuracy and…
Amir Ziaee, Erion Çano
This study introduces a new normalization layer termed Batch Layer Normalization (BLN) to reduce the problem of internal covariate shift in deep neural network layers. As a combined version of batch and layer normalization, BLN adaptively puts appropriate weight on mini-batch and feature normalization based on the…
H. Sebastian Seung
Normalization is a fundamental operation in image processing. Convolutional nets have evolved to include a large number of normalizations (29; 64; 65), and this architectural shift has proved essential for robust computer vision (27; 6; 48). Studies of biological vision, in contrast, have invoked just one or a few…
Zeming Fang, Ilona Bloem, Catherine Olsson, Wei Ji Ma + 1 more
An influential account of neuronal responses in primary visual cortex is the normalized energy model. This model is often implemented as a two-stage computation. The first stage is the extraction of contrast energy, whereby a complex cell computes the squared and summed outputs of a pair of linear filters in quadrature…
Afifa Khaled, Chao Li, Ning Jia, Kun He
Normalization techniques have been widely used in the field of deep learning due to their capability of enabling higher learning rates and are less careful in initialization. However, the effectiveness of popular normalization technologies is typically limited to specific areas. Unlike the standard Batch Normalization…
Sen Yang, Xiaobao Wang, Qijuan Yang, Enzeng Dong + 2 more
'Cosimo Distante'] The single batch normalization (BN) method is commonly used in the instance segmentation algorithms. The batch size is concerned with some drawbacks. A too small sample batch size leads to a sharp drop in accuracy, but a too large batch may result in the memory overflow of graphic processing units…
Huixia Lai, Lulu Zhang, Shi Zhang, Antonio Lázaro
As a technique for accelerating and stabilizing training, the batch normalization (BN) is widely used in deep learning. However, BN cannot effectively estimate the mean and the variance of samples when training/fine-tuning with small batches of data on resource-constrained devices. It will lead to a decrease in the…
Sébastien Herbreteau, Emmanuel Moebel, Charles Kervrann
In many information processing systems, it may be desirable to ensure that any change of the input, whether by shifting or scaling, results in a corresponding change in the system response. While deep neural networks are gradually replacing all traditional automatic processing methods, they surprisingly do not…
Authors not listed
Obtaining quantitative information about residence time behavior (i.e., the residence time distribution function) in realistic experimental systems is oftentimes experimentally challenging and numerically complex. The conventional way is to conduct very simple pulse or step tracer experiments or construct elaborate…
Tongda Xu, Yifan Shao, Yan Wang, Hongwei Qin
In recent years, there has been widespread attention drawn to convolutional neural network (CNN) based blind image quality assessment (IQA). A large number of works start by extracting deep features from CNN. Then, those features are processed through spatial average pooling (SAP) and fully connected layers to predict…
Diego E. Galvez-Aranda, Tan Le Dinh, Utkarsh Vijay, Franco M. Zanotto + 1 more
The manufacturing process of Lithium-ion battery electrodes directly affects the practical properties of the cells, such as their performance, durability, and safety. While computational physics-based modeling has been proved as a useful method to produce insights on the manufacturing properties interdependencies as…
Wai Hoh Tang, Shao Ren Sim, Daniel Ying Kia Aik, Ashwin Venkata Subba Nelanuthala + 3 more
Imaging Fluorescence Correlation Spectroscopy (Imaging FCS) is a powerful tool to extract information on molecular mobilities, actions and interactions in live cells, tissues and organisms. Nevertheless, several limitations restrict its applicability. First, FCS is data hungry, requiring 50,000 frames at 1 ms time…
Zhengfei Yang, Ping Li, Rui Wang
As a typical disease, cardiovascular and cerebrovascular diseases cause great damage to the human body. In view of the problem that the existing models failed to describe and represent the characteristics of cardiovascular and cerebrovascular indicators, convolution neural network was used to analyze the metabolic…
Yufei Gao, Jiaqi Li, Jing Xu, Qing Li + 5 more
Accurate and robust classification of medical pathology images is pivotal for computer-aided diagnosis. However, the deployment of deep learning models in high-throughput clinical screening faces a fundamental challenge: the trade-off between diagnostic accuracy and computational efficiency. Current lightweight…
Feiqing Zhang, Zhenyu Yin, Fulong Xu, Yue Li + 1 more
Rolling bearing fault diagnosis is of great significance to the safe and reliable operation of manufacturing equipment. In the actual complex environment, the collected bearing signals usually contain a large amount of noises from the resonances of the environment and other components, resulting in the nonlinear…
Mingzhe Wei, Pengcheng Xu, Junyu Liu, Xuesong Li + 9 more
Three-dimensional fluorescence microscopy often exhibits anisotropic resolution because axial information is poorly sampled and more blurred than lateral information, which complicates quantitative interpretation of fine 3D structures. Although optical remedies and computational restoration have been explored, many…
Peter Kirchweger, Lev Melnikovsky, Shahar Seifer, Michael Elbaum
Cryo-electron tomography is an expanding technology for the study of macromolecules, viruses, and cells. It is often applied to specimens that are too large or heterogeneous for methods based on 2D image averaging such as single particle analysis, e.g., intracellular membranes or organelles. Current practice records a…
Kelsey Hatzell, Yanjie Zheng
X-ray Computed Tomography (CT) is a non-invasive, non-destructive approach to imaging materials, material systems and engineered components in two- and three- dimensions. Acquisition of 3D images requires the collection of hundreds or thousands of through-thickness X-ray radiographic images from different angles. Such…
Authors not listed
Despite commonly applied corrections, known as shimming, the magnetic field in an NMR spectrometer is never perfectly homogeneous. This undesired effect distorts the lineshapes, degrades the resolution, and lowers the signal-to-noise ratio in the collected spectra. As a remedy, numerical techniques have been developed…
Robin Gutzen, Grace W Lindsay
Convolutional Neural Networks (CNNs) trained for image recognition have demonstrated remarkable conceptual similarities to the primate ventral visual pathway, but their standard feedforward architectures lack the recurrent connections that are ubiquitous in visual cortex. Such recurrence is thought to underlie…