Robust and Real-Time Bangladeshi Currency Recognition: A Dual-Stream MobileNet and EfficientNet Approach
Department of Information and Communication Engineering, Noakhali Science and Technology University, Noakhali, Bangladesh（奈卡利科学与技术大学信息与通信工程系）；Department of Computer and Communication Engineering, International Islamic University Chittagong, Chattogram, Bangladesh（国际伊斯兰大学柴坦 Nagpur 分校计算机与通信工程系）；School of Computing Sciences and Computer Engineering, University of Southern Mississippi, Hattiesburg, MS, USA（密西根南方大学计算机科学与工程学院）；Department of CSE, Netrokona University, Netrokona, Bangladesh（奈托克纳大学计算机科学与工程系）
Subreena, Mohammad Amzad Hossain, Mirza Raquib, Saydul Akbar Murad, Farida Siddiqi Prity, Muhammad Hanif, Nick Rahimi
Accurate currency recognition is essential for assistive technologies, particularly for visually impaired individuals who rely on others to identify banknotes. This dependency puts them at risk of fraud and exploitation. To address these challenges, we first build a new Bangladeshi banknote dataset that includes both controlled and real-world scenarios, ensuring a more comprehensive and diverse representation. Next, to enhance the dataset's robustness, we incorporate four additional datasets, including public benchmarks, to cover various complexities and improve the model's generalization. To overcome the limitations of current recognition models, we propose a novel hybrid CNN architecture that combines MobileNetV3-Large and EfficientNetB0 for efficient feature extraction. This is followed by an effective multilayer perceptron (MLP) classifier to improve performance while keeping computational costs low, making the system suitable for resource-constrained devices. The experimental results show that the proposed model achieves 97.95% accuracy on controlled datasets, 92.84% on complex backgrounds, and 94.98% accuracy when combining all datasets. The model's performance is thoroughly evaluated using five-fold cross-validation and seven metrics: accuracy, precision, recall, F1-score, Cohen's Kappa, MCC, and AUC. Additionally, explainable AI methods like LIME and SHAP are incorporated to enhance transparency and interpretability.
We propose a new building block, IdleBlock, which naturally prunes connections within the block. To fully utilize the IdleBlock we break the tradition of monotonic design in state-of-the-art networks, and introducing hybrid composition with IdleBlock. We study hybrid composition on MobileNet v3 and EfficientNet-B0, two of the most efficient networks. Without any neural architecture search, the deeper "MobileNet v3" with hybrid composition design surpasses possibly all state-of-the-art image recognition network designed by human experts or neural architecture search algorithms. Similarly, the h…
Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance. Based on this observation, we propose a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient. We demonstrate the effectiveness of this method on scaling up MobileNets and ResNet. To go even …
Shahjalal University of Science and Technology（沙赫贾拉尔科技大学）
Automatic detection and recognition of banknotes can be a very useful technology for people with visual difficulties and also for the banks itself by providing efficient management for handling different paper currencies. Lightweight models can easily be integrated into any handy IoT based gadgets/devices. This article presents our experiments on several state-of-the-art deep learning methods based on Lightweight Convolutional Neural Network architectures combining with transfer learning. ResNet152v2, MobileNet, and NASNetMobile were used as the base models with two different datasets containi…
The choice of activation functions is crucial for modern deep neural networks. Popular hand-designed activation functions like Rectified Linear Unit(ReLU) and its variants show promising performance in various tasks and models. Swish, the automatically discovered activation function, has been proposed and outperforms ReLU on many challenging datasets. However, it has two main drawbacks. First, the tree-based search space is highly discrete and restricted, which is difficult for searching. Second, the sample-based searching method is inefficient, making it infeasible to find specialized activat…
Google Research（谷歌研究院）；Carnegie Mellon University（卡内基梅隆大学）
Committee-based models (ensembles or cascades) construct models by combining existing pre-trained ones. While ensembles and cascades are well-known techniques that were proposed before deep learning, they are not considered a core building block of deep model architectures and are rarely compared to in recent literature on developing efficient models. In this work, we go back to basics and conduct a comprehensive analysis of the efficiency of committee-based models. We find that even the most simplistic method for building committees from existing, independently pre-trained models can match or…
Current state-of-the-art Neural Architecture Search (NAS) methods neither efficiently scale to multiple hardware platforms, nor handle diverse architectural search-spaces. To remedy this, we present DONNA (Distilling Optimal Neural Network Architectures), a novel pipeline for rapid, scalable and diverse NAS, that scales to many user scenarios. DONNA consists of three phases. First, an accuracy predictor is built using blockwise knowledge distillation from a reference model. This predictor enables searching across diverse networks with varying macro-architectural parameters such as layer types …
Alpha Reality Co（阿尔法现实公司）；IRAN Broadcasting University (IRIBU)（伊朗广播大学）
Face anti-spoofing aims at identifying the real face, as well as the fake one, and gains a high attention in security-sensitive applications, liveness detection, fingerprinting, and so on. In this paper, we address the anti-spoofing problem by proposing two end-to-end systems of convolutional neural networks. One model is developed based on the EfficientNet B0 network which has been modified in the final dense layers. The second one, is a very light model of the MobileNet V2, which has been contracted, modified and retrained efficiently on the data being created based on the Rose-Youtu dataset…
In order to classify Japanese animation-style character faces, this paper attempts to delve further into the many models currently available, including InceptionV3, InceptionResNetV2, MobileNetV2, and EfficientNet, employing transfer learning. This paper demonstrates that EfficientNet-B7, which achieves a top-1 accuracy of 85.08%, has the highest accuracy rate. MobileNetV2, which achieves a less accurate result with a top-1 accuracy of 81.92%, benefits from a significantly faster inference time and fewer required parameters. However, from the experiment, MobileNet-V2 is prone to overfitting; E…
Lightweight Image Classification of Raptor Species for Edge Devices: Rare-Species Dataset Expansion via Video Frame Extraction, Knowledge Distillation, and TensorRT Deployment
Recent convolutional neural network (CNN) development continues to advance the state-of-the-art model accuracy for various applications. However, the enhanced accuracy comes at the cost of substantial memory bandwidth and storage requirements and demanding computational resources. Although in the past the quantization methods have effectively reduced the deployment cost for edge devices, it suffers from significant information loss when processing the biased activations of contemporary CNNs. In this paper, we hence introduce an adaptive high-performance quantization method to resolve the issue…
A Hybrid Feature Fusion Deep Learning Framework for Leukemia Cancer Detection in Microscopic Blood Sample Using Gated Recurrent Unit and Uncertainty Quantification
Jagannath University（贾格纳特大学）；Green University of Bangladesh（孟加拉国绿色大学）
Massachusetts Institute of Technology（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
We address the challenging problem of efficient inference across many devices and resource constraints, especially on edge devices. Conventional approaches either manually design or use neural architecture search (NAS) to find a specialized neural network and train it from scratch for each case, which is computationally prohibitive (causing $CO_2$ emission as much as 5 cars' lifetime) thus unscalable. In this work, we propose to train a once-for-all (OFA) network that supports diverse architectural settings by decoupling training and search, to reduce the cost. We can quickly get a specialized…
Empowering Agricultural Insights: RiceLeafBD -- A Novel Dataset and Optimal Model Selection for Rice Leaf Disease Diagnosis through Transfer Learning Technique
Leading University（领先大学）；Daffodil International University（水仙国际大学）；Queensborough Community College（皇后borough社区学院）
University of Maryland（马里兰大学）；University of Southern California（南加州大学）
Large-scale training of modern deep learning models heavily relies on publicly available data on the web. This potentially unauthorized usage of online data leads to concerns regarding data privacy. Recent works aim to make unlearnable data for deep learning models by adding small, specially designed noises to tackle this issue. However, these methods are vulnerable to adversarial training (AT) and/or are computationally heavy. In this work, we propose a novel, model-free, Convolution-based Unlearnable DAtaset (CUDA) generation technique. CUDA is generated using controlled class-wise convoluti…
Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency
Attention-Guided Efficientnet Architecture For Precise Criminal Identification in Surveillance Images
Department of Computer Science and Engineering, University Visvesvaraya College of Engineering (UVCE), Bangalore University, CMR Institute of Technology, Bengaluru, India（计算机科学与工程系，Visvesvaraya工程学院（UVCE），班加罗尔大学，CMR技术学院，班加罗尔，印度）；Department of Computer Science and Engineering, University Visvesvaraya College of Engineering (UVCE), Bangalore University, Bengaluru, India（计算机科学与工程系，Visvesvaraya工程学院（UVCE），班加罗尔大学，班加罗尔，印度）
We present four different robust transfer learning and data augmentation strategies for robust mobile scene recognition. By training three mobile-ready (EfficientNetB0, MobileNetV2, MobileNetV3) and two large-scale baseline (VGG16, ResNet50) convolutional neural network architectures on the widely available Event8, Scene15, Stanford40, and MIT67 datasets, we show the generalization ability of our transfer learning strategies. Furthermore, we tested the robustness of our transfer learning strategies under viewpoint and lighting changes using the KTH-Idol2 database. Also, the impact of inference…
In this paper, the multi-task learning of lightweight convolutional neural networks is studied for face identification and classification of facial attributes (age, gender, ethnicity) trained on cropped faces without margins. The necessity to fine-tune these networks to predict facial expressions is highlighted. Several models are presented based on MobileNet, EfficientNet and RexNet architectures. It was experimentally demonstrated that they lead to near state-of-the-art results in age, gender and race recognition on the UTKFace dataset and emotion classification on the AffectNet dataset. Mor…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）
The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images. However, this often comes at a high computational cost and high memory footprint. Inspired by the fact that not all regions in an image are task-relevant, we propose a novel framework that performs efficient image classification by processing a sequence of relatively small inputs, which are strategically selected from the original image with reinforcement learning. Such a dynamic decision process naturally facilitates adaptive inference at test time, i.e., it can be terminated …
We have proposed orthogonal-Padé activation functions, which are trainable activation functions and show that they have faster learning capability and improves the accuracy in standard deep learning datasets and models. Based on our experiments, we have found two best candidates out of six orthogonal-Padé activations, which we call safe Hermite-Pade (HP) activation functions, namely HP-1 and HP-2. When compared to ReLU, HP-1 and HP-2 has an increment in top-1 accuracy by 5.06% and 4.63% respectively in PreActResNet-34, by 3.02% and 2.75% respectively in MobileNet V2 model on CIFAR100 dataset w…
Machine Learning Modeling for Real-Time Melt Pool Monitoring in Laser Powder Bed Fusion Additive Manufacturing: A Hybrid Approach
Industrial and National Institute of National Institute of Industrial and Manufacturing Engineering Standards and Technology Standards and Technology Manufacturing Engineering（工业与国家研究院国家标准化与技术研究所制造工程）
Analysis of Hyperparameter Optimization Effects on Lightweight Deep Models for Real-Time Image Classification
Homi Bhabha National Institute（霍米·巴巴国家研究所）；Variable Energy Cyclotron Centre（可变能量回旋加速器中心）；Gargi Memorial Institute of Technology（加尔吉纪念技术学院）；Jadavpur University（贾达普大学）
University of Science and Technology of China（中国科学技术大学）；UNSW Sydney（新南威尔士大学）；Genmab Inc.（Genmab公司）
NLP-based computer vision models, particularly vision transformers, have been shown to outperform CNN models in many imaging tasks. However, most digital pathology artificial-intelligence models are based on CNN architectures, probably owing to a lack of data regarding NLP models for pathology images. In this study, we developed digital pathology pipelines to benchmark the five most recently proposed NLP models (vision transformer (ViT), Swin Transformer, MobileViT, CMT, and Sequencer2D) and four popular CNN models (ResNet18, ResNet50, MobileNetV2, and EfficientNet) to predict biomarkers in co…
MoCrop: Training Free Motion Guided Cropping for Efficient Video Action Recognition
School of Computer Science, University College Dublin（计算机科学学院，都柏林大学学院）；Undergraduate School of Artificial Intelligence, Shenzhen Polytechnic University（人工智能本科学院，深圳职业技术大学）；School of Electrical and Electronic Engineering, University College Dublin（电子与电气工程学院，都柏林大学学院）
