arXiv subjects

Mahmood Fathy

Publications and source records attributed to Mahmood Fathy.

At least 19 recordsLinked to original sources

arXiv2023

A Survey on Multi-Objective Neural Architecture Search

Recently, the expert-crafted neural architectures is increasing overtaken by the utilization of neural architecture search (NAS) and automatic generation (and tuning) of network structures which has a close relation to the Hyperparameter Optimization and Auto Machine Learning (AutoML). After the earlier NAS attempts to optimize only the prediction accuracy, Multi-Objective Neural architecture Search (MONAS) has been attracting attentions which considers more goals such as computational complexity, power consumption, and size of the network for optimization, reaching a trade-off between the accuracy and other features like the computational cost. In this paper, we present an overview of principal and state-of-the-art works in the field of MONAS. Starting from a well-categorized taxonomy and formulation for the NAS, we address and correct some miscategorizations in previous surveys of the NAS field. We also provide a list of all known objectives used and add a number of new ones and elaborate their specifications. We have provides analyses about the most important objectives and shown that the stochastic properties of some the them should be differed from deterministic ones in the multi-objective optimization procedure of NAS. We finalize this paper with a number of future directions and topics in the field of MONAS.

cs.CV↗

arXiv2022

Energy-efficient Non Uniform Last Level Caches for Chip-multiprocessors Based on Compression

With technology scaling, the size of cache systems in chip-multiprocessors (CMPs) has been dramatically increased to efficiently store and manipulate a large amount of data in future applications and decrease the gap between cores and off-chip memory accesses. For future CMPs architecting, 3D stacking of LLCs has been recently introduced as a new methodology to combat to performance challenges of 2D integration and the memory wall. However, the 3D design of SRAM LLCs has made the thermal problem even more severe. It, therefore, incurs more leakage energy consumption than conventional SRAM cache architectures in 2Ds due to dense integration. In this paper, we propose two different architectures that exploit the data compression to reduce the energy of LLC and interconnects in 3D-ICs.

cs.AR↗

arXiv2021

Image/Video Deep Anomaly Detection: A Survey

The considerable significance of Anomaly Detection (AD) problem has recently drawn the attention of many researchers. Consequently, the number of proposed methods in this research field has been increased steadily. AD strongly correlates with the important computer vision and image processing tasks such as image/video anomaly, irregularity and sudden event detection. More recently, Deep Neural Networks (DNNs) offer a high performance set of solutions, but at the expense of a heavy computational cost. However, there is a noticeable gap between the previously proposed methods and an applicable real-word approach. Regarding the raised concerns about AD as an ongoing challenging problem, notably in images and videos, the time has come to argue over the pitfalls and prospects of methods have attempted to deal with visual AD tasks. Hereupon, in this survey we intend to conduct an in-depth investigation into the images/videos deep learning based AD methods. We also discuss current challenges and future research directions thoroughly.

cs.CV↗

arXiv2021

DV-DVFS: Merging Data Variety and DVFS Technique to Manage the Energy Consumption of Big Data Processing

Data variety is one of the most important features of Big Data. Data variety is the result of aggregating data from multiple sources and uneven distribution of data. This feature of Big Data causes high variation in the consumption of processing resources such as CPU consumption. This issue has been overlooked in previous works. To overcome the mentioned problem, in the present work, we used Dynamic Voltage and Frequency Scaling (DVFS) to reduce the energy consumption of computation. To this goal, we consider two types of deadlines as our constraint. Before applying the DVFS technique to computer nodes, we estimate the processing time and the frequency needed to meet the deadline. In the evaluation phase, we have used a set of data sets and applications. The experimental results show that our proposed approach surpasses the other scenarios in processing real datasets. Based on the experimental results in this paper, DV-DVFS can achieve up to 15% improvement in energy consumption.

cs.PF↗

arXiv2020

Multi-level Context Gating of Embedded Collective Knowledge for Medical Image Segmentation

Medical image segmentation has been very challenging due to the large variation of anatomy across different cases. Recent advances in deep learning frameworks have exhibited faster and more accurate performance in image segmentation. Among the existing networks, U-Net has been successfully applied on medical image segmentation. In this paper, we propose an extension of U-Net for medical image segmentation, in which we take full advantages of U-Net, Squeeze and Excitation (SE) block, bi-directional ConvLSTM (BConvLSTM), and the mechanism of dense convolutions. (I) We improve the segmentation performance by utilizing SE modules within the U-Net, with a minor effect on model complexity. These blocks adaptively recalibrate the channel-wise feature responses by utilizing a self-gating mechanism of the global information embedding of the feature maps. (II) To strengthen feature propagation and encourage feature reuse, we use densely connected convolutions in the last convolutional layer of the encoding path. (III) Instead of a simple concatenation in the skip connection of U-Net, we employ BConvLSTM in all levels of the network to combine the feature maps extracted from the corresponding encoding path and the previous decoding up-convolutional layer in a non-linear way. The proposed model is evaluated on six datasets DRIVE, ISIC 2017 and 2018, lung segmentation, $PH^2$, and cell nuclei segmentation, achieving state-of-the-art performance.

eess.IV↗

arXiv2020

Deep-HR: Fast Heart Rate Estimation from Face Video Under Realistic Conditions

This paper presents a novel method for remote heart rate (HR) estimation. Recent studies have proved that blood pumping by the heart is highly correlated to the intense color of face pixels, and surprisingly can be utilized for remote HR estimation. Researchers successfully proposed several methods for this task, but making it work in realistic situations is still a challenging problem in computer vision community. Furthermore, learning to solve such a complex task on a dataset with very limited annotated samples is not reasonable. Consequently, researchers do not prefer to use the deep learning approaches for this problem. In this paper, we propose a simple yet efficient approach to benefit the advantages of the Deep Neural Network (DNN) by simplifying HR estimation from a complex task to learning from very correlated representation to HR. Inspired by previous work, we learn a component called Front-End (FE) to provide a discriminative representation of face videos, afterward a light deep regression auto-encoder as Back-End (BE) is learned to map the FE representation to HR. Regression task on the informative representation is simple and could be learned efficiently on limited training samples. Beside of this, to be more accurate and work well on low-quality videos, two deep encoder-decoder networks are trained to refine the output of FE. We also introduce a challenging dataset (HR-D) to show that our method can efficiently work in realistic conditions. Experimental results on HR-D and MAHNOB datasets confirm that our method could run as a real-time method and estimate the average HR better than state-of-the-art ones.

cs.CV↗

arXiv2019

An Energy-Efficient Heterogeneous Memory Architecture for Future Dark Silicon Embedded Chip-Multiprocessors

Main memories play an important role in overall energy consumption of embedded systems. Using conventional memory technologies in future designs in nanoscale era causes a drastic increase in leakage power consumption and temperature-related problems. Emerging non-volatile memory (NVM) technologies offer many desirable characteristics such as near-zero leakage power, high density and non-volatility. They can significantly mitigate the issue of memory leakage power in future embedded chip-multiprocessor (eCMP) systems. However, they suffer from challenges such as limited write endurance and high write energy consumption which restrict them for adoption in modern memory systems. In this article, we present a convex optimization model to design a 3D stacked hybrid memory architecture in order to minimize the future embedded systems energy consumption in the dark silicon era. This proposed approach satisfies endurance constraint in order to design a reliable memory system. Our convex model optimizes numbers and placement of eDRAM and STT-RAM memory banks on the memory layer to exploit the advantages of both technologies in future eCMPs. Energy consumption, the main challenge in the dark silicon era, is represented as a major target in this work and it is minimized by the detailed optimization model in order to design a dark silicon aware 3D Chip-Multiprocessor. Experimental results show that in comparison with the Baseline memory design, the proposed architecture improves the energy consumption and performance of the 3D CMP on average about 61.33 and 9 percent respectively.

cs.AR↗

arXiv2019

Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions

In recent years, deep learning-based networks have achieved state-of-the-art performance in medical image segmentation. Among the existing networks, U-Net has been successfully applied on medical image segmentation. In this paper, we propose an extension of U-Net, Bi-directional ConvLSTM U-Net with Densely connected convolutions (BCDU-Net), for medical image segmentation, in which we take full advantages of U-Net, bi-directional ConvLSTM (BConvLSTM) and the mechanism of dense convolutions. Instead of a simple concatenation in the skip connection of U-Net, we employ BConvLSTM to combine the feature maps extracted from the corresponding encoding path and the previous decoding up-convolutional layer in a non-linear way. To strengthen feature propagation and encourage feature reuse, we use densely connected convolutions in the last convolutional layer of the encoding path. Finally, we can accelerate the convergence speed of the proposed network by employing batch normalization (BN). The proposed model is evaluated on three datasets of: retinal blood vessel segmentation, skin lesion segmentation, and lung nodule segmentation, achieving state-of-the-art performance.

eess.IV↗

arXiv2018

AVID: Adversarial Visual Irregularity Detection

Real-time detection of irregularities in visual data is very invaluable and useful in many prospective applications including surveillance, patient monitoring systems, etc. With the surge of deep learning methods in the recent years, researchers have tried a wide spectrum of methods for different applications. However, for the case of irregularity or anomaly detection in videos, training an end-to-end model is still an open challenge, since often irregularity is not well-defined and there are not enough irregular samples to use during training. In this paper, inspired by the success of generative adversarial networks (GANs) for training deep models in unsupervised or self-supervised settings, we propose an end-to-end deep network for detection and fine localization of irregularities in videos (and images). Our proposed architecture is composed of two networks, which are trained in competing with each other while collaborating to find the irregularity. One network works as a pixel-level irregularity Inpainter, and the other works as a patch-level Detector. After an adversarial self-supervised training, in which I tries to fool D into accepting its inpainted output as regular (normal), the two networks collaborate to detect and fine-segment the irregularity in any given testing video. Our results on three different datasets show that our method can outperform the state-of-the-art and fine-segment the irregularity.

cs.CV↗

arXiv2018

Online Signature Verification using Deep Representation: A new Descriptor

This paper presents an accurate method for verifying online signatures. The main difficulty of signature verification come from: (1) Lacking enough training samples (2) The methods must be spatial change invariant. To deal with these difficulties and modeling the signatures efficiently, we propose a method that a one-class classifier per each user is built on discriminative features. First, we pre-train a sparse auto-encoder using a large number of unlabeled signatures, then we applied the discriminative features, which are learned by auto-encoder to represent the training and testing signatures as a self-thought learning method (i.e. we have introduced a signature descriptor). Finally, user's signatures are modeled and classified using a one-class classifier. The proposed method is independent on signature datasets thanks to self-taught learning. The experimental results indicate significant error reduction and accuracy enhancement in comparison with state-of-the-art methods on SVC2004 and SUSIG datasets.

cs.CV↗

arXiv2018

Semantic Video Segmentation: A Review on Recent Approaches

This paper gives an overview on semantic segmentation consists of an explanation of this field, it's status and relation with other vision fundamental tasks, different datasets and common evaluation parameters that have been used by researchers. This survey also includes an overall review on a variety of recent approaches (RDF, MRF, CRF, etc.) and their advantages and challenges and shows the superiority of CNN-based semantic segmentation systems on CamVid and NYUDv2 datasets. In addition, some areas that is ideal for future work have mentioned.

cs.CV↗

arXiv2018

Adversarially Learned One-Class Classifier for Novelty Detection

Novelty detection is the process of identifying the observation(s) that differ in some respect from the training observations (the target class). In reality, the novelty class is often absent during training, poorly sampled or not well defined. Therefore, one-class classifiers can efficiently model such problems. However, due to the unavailability of data from the novelty class, training an end-to-end deep network is a cumbersome task. In this paper, inspired by the success of generative adversarial networks for training deep models in unsupervised and semi-supervised settings, we propose an end-to-end architecture for one-class classification. Our architecture is composed of two deep networks, each of which trained by competing with each other while collaborating to understand the underlying concept in the target class, and then classify the testing samples. One network works as the novelty detector, while the other supports it by enhancing the inlier samples and distorting the outliers. The intuition is that the separability of the enhanced inliers and distorted outliers is much better than deciding on the original samples. The proposed framework applies to different related applications of anomaly and outlier detection in images and videos. The results on MNIST and Caltech-256 image datasets, along with the challenging UCSD Ped2 dataset for video anomaly detection illustrate that our proposed method learns the target class effectively and is superior to the baseline and state-of-the-art methods.

cs.CV↗

arXiv2018

Test Generation and Scheduling for a Hybrid BIST Considering Test Time and Power Constraint

This paper presents a novel approach for test generation and test scheduling for multi-clock domain SoCs. A concurrent hybrid BIST architecture is proposed for testing cores. Furthermore, a heuristic for selecting cores to be tested concurrently and order of applying test patterns is proposed. Experimental results show that the proposed heuristics give us an optimized method for multi clock domain SoC testing in comparison with the previous works.

cs.DC↗

arXiv2017

BILBO-friendly Hybrid BIST Architecture with Asymmetric Polynomial Reseeding

By advances in technology, integrated circuits have come to include more functionality and more complexity in a single chip. Although methods of testing have improved, but the increase in complexity of circuits, keeps testing a challenging problem. Two important challenges in testing of digital circuits are test time and accessing the circuit under test (CUT) for testing. These challenges become even more important in complex system on chip (SoC) zone. This paper presents a multistage test strategy to be implemented on a BIST architecture for reducing test time of a simple core as solution for more global application of SoC testing strategy. This strategy implements its test pattern generation and output response analyzer in a BILBO architecture. The proposed method benefits from an irregular polynomial BILBO (IP-BILBO) structure to improve its test results. Experimental results on ISCAS-89 benchmark circuits show an average of 35% improvement in test time in proportion to pervious work.

cs.AR↗

arXiv2017

An Improved Scheme for Pre-computed Patterns in Core-based SoC Architecture

By advances in technology, integrated circuits have come to include more functionality and more complexity in a single chip. Although methods of testing have improved, but the increase in complexity of circuits, keeps testing a challenging problem. Two important challenges in testing of digital circuits are test time and accessing the circuit under test (CUT) for testing. These challenges become even more important in complex system on chip (SoC) zone. This paper presents an improved scheme for generating precomputed test patterns in core based systems on chip. This approach reduces the number of pre computed test patterns and as the result, test application time (TAT) will be decreased. Experimental results on ISCAS89 benchmark circuits show improvement in the number of test clock cycles.

cs.DC↗

arXiv2017

Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes

The detection of abnormal behaviours in crowded scenes has to deal with many challenges. This paper presents an efficient method for detection and localization of anomalies in videos. Using fully convolutional neural networks (FCNs) and temporal data, a pre-trained supervised FCN is transferred into an unsupervised FCN ensuring the detection of (global) anomalies in scenes. High performance in terms of speed and accuracy is achieved by investigating the cascaded detection as a result of reducing computation complexities. This FCN-based architecture addresses two main tasks, feature representation and cascaded outlier detection. Experimental results on two benchmarks suggest that detection and localization of the proposed method outperforms existing methods in terms of accuracy.

cs.CV↗

arXiv2017

IDSA: Intelligent Distributed Sensor Activation Algorithm For Target Tracking With Wireless Sensor Network

One important application of the Wireless Sensor Network(WSN) is target tracking, the aim of this application is converging to an event or object in an area. In this paper, we propose an energy-efficient distributed sensor activation protocol based on predicted location technique, called Intelligent Distributed Sensor Activation Algorithm (IDSA). The proposed algorithm predicts the location of target in the next time interval, by analyzing current location and movement history of the target, this prediction is done by computational intelligence. The fewest essential number of sensor nodes within the predicted location will be activated to cover the target. The results show that the proposed method outperforms the existing methods such as Naïve and DSA in terms of energy consumption and the number of nodes that was involved in tracking the target.

cs.NI↗

arXiv2016

STFCN: Spatio-Temporal FCN for Semantic Video Segmentation

This paper presents a novel method to involve both spatial and temporal features for semantic video segmentation. Current work on convolutional neural networks(CNNs) has shown that CNNs provide advanced spatial features supporting a very good performance of solutions for both image and video analysis, especially for the semantic segmentation task. We investigate how involving temporal features also has a good effect on segmenting video data. We propose a module based on a long short-term memory (LSTM) architecture of a recurrent neural network for interpreting the temporal characteristics of video frames over time. Our system takes as input frames of a video and produces a correspondingly-sized output; for segmenting the video our method combines the use of three components: First, the regional spatial features of frames are extracted using a CNN; then, using LSTM the temporal features are added; finally, by deconvolving the spatio-temporal features we produce pixel-wise predictions. Our key insight is to build spatio-temporal convolutional networks (spatio-temporal CNNs) that have an end-to-end architecture for semantic video segmentation. We adapted fully some known convolutional network architectures (such as FCN-AlexNet and FCN-VGG16), and dilated convolution into our spatio-temporal CNNs. Our spatio-temporal CNNs achieve state-of-the-art semantic segmentation, as demonstrated for the Camvid and NYUDv2 datasets.

cs.CV↗