Analysis of convolutional neural network architectures for machine vision systems

Ultrasound (US) is the preferred modality for fatty liver disease diagnosis due to its noninvasive, real-time, and cost-effective imaging capabilities. However, traditional B-mode US is qualitative, and therefore, the assessment is very subjective. Computer-aided diagnostic tools can improve the specificity and sensitivity of US and help clinicians to perform uniform diagnoses. In this work, we propose a novel deep learning model for nonalcoholic fatty liver disease classification from US data. We design a multi-feature guided multi-scale residual convolutional neural network (CNN) architecture to capture features of different receptive fields. B-mode US images are combined with their corresponding local phase filtered images and radial symmetry transformed images as multi-feature inputs for the network. Various fusion strategies are studied to improve prediction accuracy. We evaluate the designed network architectures on B-mode in vivo liver US images collected from 55 subjects. We also provide quantitative results by comparing our proposed multi-feature CNN architecture against traditional CNN designs and machine learning methods. Quantitative results show an average classification accuracy above 90% over tenfold cross-validation. Our proposed method achieves a 97.8% area under the ROC curve (AUC) for the patient-specific leave-one-out cross-validation (LOOCV) evaluation. Comprehensive validation results further demonstrate that our proposed approaches achieve significant improvements compared to training mono-feature CNN architectures ([Formula: see text]). Feature combination is valuable for the traditional classification methods, and the use of multi-scale CNN can improve liver classification accuracy. Based on the promising performance, the proposed method has the potential in practical applications to help radiologists diagnose nonalcoholic fatty liver disease.

Large deep neural network (DNN) models pose significant computational and memory challenges, particularly when deploying them on edge devices. To address this, techniques such as pruning, quantization, data sparsity, and data reuse have been applied to DNNs, mitigating memory and computational complexity at the cost of some accuracy loss. This paper introduces an efficient hardware accelerator tailored for Convolutional Neural Networks (CNNs). The proposed architecture is the result of a co-optimized approach encompassing both algorithms and hardware. It leverages linear approximation of pre-trained network weights with minimal accuracy loss. A novel computational reuse method is presented to curtail the number of multiplication and addition operations and memory accesses, seamlessly integrated into the dedicated elements within the CNN design. To validate the effectiveness of this architecture, we conducted experiments on a gem5-based RISCV simulator, employing the VGG16 model for the CIFAR 100 dataset and the AlexNet model for the TinyImageNet dataset. The results showcased an impressive speedup of approximately $2\times$ on AlexNet compared to the reference model. Additionally, our proposed CNN design was successfully implemented on the Xilinx Kintex 7 Field Programmable Gate Array (FPGA), achieving a notable reduction in hardware resource utilization compared to prior research efforts. This work serves as a versatile framework for evaluating diverse trade-offs involving accuracy, latency, power consumption, and cost across different CNN architectures.

Recognition of human activity based on convolutional neural network has received the interest of researchers in recent years due to its significant improvement in accuracy. A large number of algorithms based on the deep learning approach have been proposed for activity recognition purpose. However, with the increasing advancements in technologies having limited computational resources, it needs to design an efficient deep learning-based approaches with improved utilization of computational resources. This paper presents a simple and efficient 2-Dimensional convolutional neural network (2-D CNN) architecture with very small size convolutional kernel for human activity recognition. The merit of the proposed CNN architecture over standard deep learning architectures is fewer trainable parameters and lesser memory requirement which enables it to train the proposed CNN architecture on low GPU memory-based devices and also works well with smaller as well as larger size datasets. The proposed approach consists of mainly four stages: namely (1) creation of dataset and data augmentation, (2) designing 2-D convolutional neural network (CNN) architecture, (3) the proposed 2-D CNN architecture trained from scratch up to optimum stage, and (4) evaluation of the trained 2-D CNN architecture. To illustrate the effectiveness of the proposed architecture several extensive experiments are conducted on three publicly available datasets, namely IXMAS, YouTube, and UCF101 dataset. The results of the proposed method and its comparison with other state-of-the-art methods [8-12,14,18-26,29-33] demonstrate the usefulness of the proposed method.

In this paper, we study the performance of variants of well-known Convolutional Neural Network (CNN) architectures on different audio tasks. We show that tuning the Receptive Field (RF) of CNNs is crucial to their generalization. An insufficient RF limits the CNN's ability to fit the training data. In contrast, CNNs with an excessive RF tend to over-fit the training data and fail to generalize to unseen testing data. As state-of-the-art CNN architectures - in computer vision and other domains - tend to go deeper in terms of number of layers, their RF size increases and therefore they degrade in performance in several audio classification and tagging tasks. We study well-known CNN architectures and how their building blocks affect their receptive field. We propose several systematic approaches to control the RF of CNNs and systematically test the resulting architectures on different audio classification and tagging tasks and datasets. The experiments show that regularizing the RF of CNNs using our proposed approaches can drastically improve the generalization of models, out-performing complex architectures and pre-trained models on larger datasets. The proposed CNNs achieve state-of-the-art results in multiple tasks, from acoustic scene classification to emotion and theme detection in music to instrument recognition, as demonstrated by top ranks in several pertinent challenges (DCASE, MediaEval).

Every year, new Convolutional Neural Network (CNN) architectures appear to deal with different problems in the activity of image and video recognition. These architectures usually work along the ImageNet dataset for looking for the best performance of the CNNs without taking into account the video task where they are used. This can represent a problem if the task is Human Action Recognition (HAR) in video, since the CNN architectures are pre-trained with an image dataset that can practically contain any object, while HAR problem requires consecutive frames of people doing actions. To prove the idea that using CNNs pre-trained on an image dataset does not always achieve the best performance on a video dataset and that, therefore, it is worth comparing the performance of different CNNs under similar circumstances for the HAR problem, this work proposes an analysis between eight different CNN architectures. Each one of the CNN was exclusively trained with RGB images, which were extracted from the frames of the different classes of videos of HMDB51 dataset. To make the classification of an activity in video, we average the predictions taking into account the successes. We also made some ensembles with the best performance CNNs to measure the improvement in accuracy. Our results suggest that Xception is a strong baseline model that could be used by the community to make their comparisons of their proposals more robust.

In this paper, the Convolutional Neural Network (CNN) architecture, which is one of the deep learning architectures, is used to classify the basic circuit components drawn by hand. During the training and testing stages of the model, a new dataset containing images of 863 circuit components manually drawn by different people is created. The data set contains images of four different classes of circuit components such as resistor, inductor, capacitor and voltage source. All images have been fixed to the same size and converted to grayscale to increase recognition performance and reduce process complexity. In the study, training for four classes is performed with CNN architecture. Based on the CNN architecture, four new CNN models are employed with different the number of layers. The training and validation results of these models are compared separately, the model with the highest training and validation performance is observed with four layer CNN model (CNN-4). This model obtained 84.41% accuracy rate at classification task.

Simple SummaryThe assistance of computer image analysis that automatically identifies tissue or cell types has greatly improved histopathologic interpretation and diagnosis accuracy. In this paper, the Convolutional Neural Network (CNN) has been adapted to predict and classify lymph node metastasis in breast cancer. We observe that image resolutions of lymph node metastasis datasets in breast cancer usually are quite smaller than the designed model input resolution, which defects the performance of the proposed model. To mitigate this problem, we propose a boosted CNN architecture and a novel data augmentation method called Random Center Cropping (RCC). Different from traditional image cropping methods only suitable for resolution images in large scale, RCC not only enlarges the scale of datasets but also preserves the resolution and the center area of images. In addition, the downsampling scale of the network is diminished to be more suitable for small resolution images. Furthermore, we introduce attention and feature fusion mechanisms to enhance the semantic information of image features extracted by CNN. Experiments illustrate that our methods significantly boost performance of fundamental CNN architectures, where the best-performed method achieves an accuracy of 97.96% ± 0.03% and an Area Under the Curve (AUC) of 99.68% ± 0.01% in Rectified Patch Camelyon (RPCam) datasets, respectively.(1) Purpose: To improve the capability of EfficientNet, including developing a cropping method called Random Center Cropping (RCC) to retain the original image resolution and significant features on the images’ center area, reducing the downsampling scale of EfficientNet to facilitate the small resolution images of RPCam datasets, and integrating attention and Feature Fusion (FF) mechanisms with EfficientNet to obtain features containing rich semantic information. (2) Methods: We adopt the Convolutional Neural Network (CNN) to detect and classify lymph node metastasis in breast cancer. (3) Results: Experiments illustrate that our methods significantly boost performance of basic CNN architectures, where the best-performed method achieves an accuracy of 97.96% ± 0.03% and an Area Under the Curve (AUC) of 99.68% ± 0.01% on RPCam datasets, respectively. (4) Conclusions: (1) To our limited knowledge, we are the only study to explore the power of EfficientNet on Metastatic Breast Cancer (MBC) classification, and elaborate experiments are conducted to compare the performance of EfficientNet with other state-of-the-art CNN models. It might provide inspiration for researchers who are interested in image-based diagnosis using Deep Learning (DL). (2) We design a novel data augmentation method named RCC to promote the data enrichment of small resolution datasets. (3) All of our four technological improvements boost the performance of the original EfficientNet.

Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks. From an image and signal processing point of view, this success might be a bit surprising as the inherent spatial pyramid design of most CNNs is apparently violating basic signal processing laws, i.e. Sampling Theorem in their down-sampling operations. However, since poor sampling appeared not to affect model accuracy, this issue has been broadly neglected until model robustness started to receive more attention. Recent work [18] in the context of adversarial attacks and distribution shifts, showed after all, that there is a strong correlation between the vulnerability of CNNs and aliasing artifacts induced by poor down-sampling operations. This paper builds on these findings and introduces an aliasing free down-sampling operation which can easily be plugged into any CNN architecture: FrequencyLowCut pooling. Our experiments show, that in combination with simple and Fast Gradient Sign Method (FGSM) adversarial training, our hyper-parameter free operator substantially improves model robustness and avoids catastrophic overfitting. Our code is available at https://github.com/GeJulia/flc_pooling.KeywordsCNNsAdversarial robustnessAliasing

A Brain Computer Interface (BCI) character speller allows human-beings to directly spell characters using eye-gazes, thereby building communication between the human brain and a computer. Convolutional Neural Networks (CNNs) have achieved state-of-the-art results on the BCI character spelling accuracy. Unfortunately, to the best of our knowledge, it has not been studied whether the CNN should be designed differently to increase the spelling accuracy when the number of sensors used to acquire EEG signals is different. This paper performs an empirical study to investigate this issue. First, we show a motivational example which motivates us for this investigation. Then, we propose a method to design CNNs according to the number of sensors used in the BCI character speller. This method automatically configures a parametric CNN we have devised according to the given number of sensors. Experimental results on six datasets show that we need to design different CNNs when different number of sensors are used for the acquisition of EEG signals. Experimental results also show that our designed sensor-aware CNNs outperform other CNNs in terms of spelling accuracy in most cases. Our CNNs can increase the spelling accuracy achieved by other CNNs with up to 34%.

Convolutional Neural Networks (CNNs) have become foundational in addressing image-based tasks across diverse domains such as medical imaging, autonomous driving, remote sensing, and surveillance. Recent developments in CNN architectures have significantly enhanced model performance, efficiency, and generalization capabilities. Innovations such as residual connections, depthwise separable convolutions, attention mechanisms, and hybrid models combining CNNs with transformers have led to breakthroughs in image classification, object detection, image segmentation, and super-resolution. In addition, advances in training strategies, including self-supervised learning and transfer learning, have expanded the applicability of CNNs to scenarios with limited labeled data. This paper reviews and synthesizes the latest advancements in CNN architectures and training techniques, analyzes their performance across key benchmarks, and discusses ongoing challenges and future research directions in the field of image-based AI systems.

Although font recognition is a fundamental issue in the field of document analysis and recognition, it was usually ignored in the past. With the development of optical character recognition (OCR), font recognition becomes more and more important. This paper proposed a well-designed convolutional neural network (CNN) architecture for traditional Mongolian font recognition by means of a single word. To be specific, the whole word image is regarded as input of CNN. Hence, the word images should be normalized into the same size before being inputted into CNN. By comparison, an appropriate aspect ratio for the traditional Mongolian word images has been determined. Experimental results demonstrate that the proposed CNN architecture outperforms three classic CNN architectures, including LeNet-5, AlexNet and GoogLeNet. Therefore, the proposed CNN is much more suitable for the task of the traditional Mongolian font recognition in the way of a single word.

Classification performance based on ImageNet is the de-facto standard metric for CNN development. In this work we challenge the notion that CNN architecture design solely based on ImageNet leads to generally effective convolutional neural network (CNN) architectures that perform well on a diverse set of datasets and application domains. To this end, we investigate and ultimately improve ImageNet as a basis for deriving such architectures. We conduct an extensive empirical study for which we train 500 CNN architectures, sampled from the broad AnyNetX design space, on ImageNet as well as 8 additional well-known image classification benchmark datasets from a diverse array of application domains. We observe that the performances of the architectures are highlydataset dependent. Some datasets even exhibit a negative error correlation with ImageNet across all architectures. We show how to significantly increase these correlations byutilizing ImageNet subsets restricted to fewer classes. These contributions can have a profound impact on the way we design future CNN architectures and help alleviate the tilt we see currently in our community with respect to over-reliance on one dataset.

Deep Learning (DL) is a fastest growing and a broader part of machine learning family. Deep learning uses Convolutional Neural Networks (CNN) for image classification as it gives the most accurate results in solving real- world problem. CNN has various pre-trained architecture like AlexNet, GoogleNet, DenseNet, SqueezeNet, ResNet, VGGNet etc. In this study, we have used CNN and AlexNet architecture for detecting the disease in Mango and Potato leaf and compare the accuracy and efficiency between these architectures. The dataset containing 4004 images were used for this work. The images for potato were taken from plantvillage website, while images for mango were collected from GBPUAT field location. The results show that accuracy achieved from AlexNet is higher than CNN architecture.

Convolutional Neural Network (CNN) architectures for the classification of remote sensing images have been in use for the last 6 years. These CNN architectures are preferred over other standard classifiers, such as SVM and Multilayer perceptron, due to their ability to automatically extract features from image patches. Recently, attention-based models have been used for remote sensing classification because of their ability to concentrate on a few relevant features while ignoring others. To mimic the behavior of the human retina’s ganglia neuron, the concept of On-Off Center-Surround (OOCS) filters has recently been introduced with CNN. This study is an attempt to use both OOCS and attention based deep learning architecture with CNN using two remote sensing datasets. Results suggest that the use of both OOCS and the attention layer does not improve classification accuracy in comparison to the CNN model only.

Bangla handwritten character recognition is a popular research topic as its difficulty is higher than the recognition of other languages because of multiple formats of compound characters. State of the art Convolutional neural network (CNN) architectures are very much useful in computer vision applications. Some works have been carried out in Bangla handwritten character recognition but most of them either not very efficient or they can not classify a lot of characters. In this work, state of art pre-trained CNN architectures is used to classify 231 different Bangla handwritten characters using CMATERdb dataset. The images were first converted to B&W form with white as the foreground color. The size of the images is reduced to 28 × 28 form. These images are used as input to the CNN architectures. The weights of the state-of-the-art CNN models are kept as it was. The training learning rate was set to 0.001 and categorical cross-entropy as the error function. After 50 epochs, InceptionResNetV2 achieved the best accuracy (96.99%). DenseNet121 and InceptionNetV3 also provided remarkable recognition accuracy (96.55 and 96.20%, respectively). We also considered combination of trained InceptionResNetV2, InceptionNetV3 and DenseNet121 architectures which provided better recognition accuracy (97.69%) than other single CNN architectures but it is not feasible for using as it requires a lot of computation power and memory. The models were tested in the cases where characters look confusing to humans, but all the architectures showed equal capability in recognizing these images. Considering computational complexity, memory and capability of recognizing confused characters, InceptionResNetV2 can be said as the best performing model.