RECENT DEVELOPMENTS IN CONVOLUTIONAL NEURAL NETWORKS FOR IMAGE-BASED TASKS

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.

An in-depth analysis of Convolutional Neural Network architectures with transfer learning for skin disease diagnosis

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.

Purpose This study aims to automate the visual inspection of piling sheets in water channel construction using artificial intelligence (AI). By employing image classification and object detection techniques, the research focuses on extracting and analysing geometric features to enhance the accuracy and efficiency of the inspection process. It also addresses key challenges associated with the unique characteristics of construction materials and the limited variability of available inspection datasets. Design/methodology/approach Convolutional neural networks (CNNs) with varying complexities are employed for image classification, across four and six classes, and for object detection of piling sheets in water channel environments. A dataset provided by Witteveen + Bos is preprocessed to generate training sets, and the CNN architectures are optimized for enhanced performance. The accuracy and efficiency of the proposed models are evaluated and compared against traditional manual inspection methods. Findings The AI-driven approach significantly reduces processing time, evaluating 40,000 images in just 11.9 h, compared to approximately one month using manual assessment. The 4-class classification model achieves an accuracy of 96%, while the 6-class model attains 72%. The object detection model produces a mean average precision (mAP) of 79%. These results meet the performance standards set by the Dutch company Witteveen + Bos, which demonstrate the effectiveness of AI in automating the inspection of piling sheets. Originality/value This study introduces a novel AI-based approach for assessing piling sheets, demonstrating substantial improvements over traditional inspection methods. It introduces a systematic evaluation of various CNN architectures and hyperparameters to optimize the models specifically for piling sheet inspection rather than relying on off-the-shelf solutions. The use of CNNs for both image classification and object detection adheres to relevant Dutch engineering standards. Notably, the reduction in processing time, from one month to around 12 h, represents a major advancement in the efficiency of civil engineering inspections.

The convolutional neural network (CNN) architecture has shown remarkable success in image classification and segmentation. Its popularity has increased promptly due to various factors such as exponential growth in computational resources, availability of benchmark datasets, supporting libraries, and open-source software. The efficiency of CNN architecture majorly depends on the complexity of the architecture, availability of datasets, and hyperparameter selection. But, due to the huge number of parameters in CNN architecture, its selection has completely remained ad hoc in the past works. In this article, a novel encoding technique has been proposed that can represent complex CNN architecture effectively. The article defines basic building blocks to represent CNN architecture such as the genesis block, transit block, agile block, and output block. This encoding structure is used to generate dynamic length chromosome structure and initialized using evolutionary algorithms. A comparative analysis is also presented that shows compared its effectiveness with existing encoding representations on the basis of the number of encoding parameters, training cost, and efficiency.

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.

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.

Domain- and task-specific transfer learning for medical segmentation tasks

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.

Chapter 2 - Convolution neural network and deep learning

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.

In recent years, Convolutional Neural Networks (CNNs) have been widely successful for numerous computer vision tasks using 2D color and 3D point data, such as object detection and classification, and 3D pose estimation. Despite these successes, it comes with a price --- CNNs require a vast amount of labeled training data to be successful. Many training datasets are now available, however, they are mostly limited to general objects in the public domain such as people, cars, buildings, fruit, and more. Thus, not all fields have sufficient training data. Even if an adequate number of data samples can be built into a dataset, manually collecting and labeling the training data remains a laborious task. Several approaches to reduce or eradicate the need for training data have been proposed by researchers. The two most popular approaches are training with synthetic data and training on generalized object features. Training with synthetic data refers to the use of computer graphics to generate training data. While this approach has demonstrated success, it comes with its own challenges. In contrast, training a CNN on generalized object features identifies specific local 3D features or control points on objects. Local 3D features and their descriptors have proven in the past to be universally applicable and effective for general object detection, and thus, this method allows for a generalized CNN. A generalized CNN refers to a network architecture that, after initial training, can be specialized for a new task with a minimum amount or no new training data. This dissertation investigates an encoder-decoder architecture and determines the capabilities of it to generalize the CNN architecture for object detection tasks in point cloud data. A CNN is trained to recognize 3D features and demonstrates, without retraining, its successful applicability for point cloud object detection using disparate data. Additionally, the geometric consistency of the descriptors is evaluated to obtain further insight. The results demonstrate that the proposed 3D feature descriptors, and their increased geometric consistency contribute to the increased encoder-decoder architecture performance. In summary, this dissertation contributes a state-of-the-art, generalized, feature descriptor-based CNN architecture that can be transferred to different objects without retraining. Furthermore, it provides insight explaining the increased performance of the CNN compared to the state-of-the-art.

Image classification is an important task that has a wide range of applications. Convolutional neural networks (CNNs) are a common approach that can achieve promising performance in image classification. However, using CNNs to address a problem requires in-depth knowledge about CNN architectures and how it relates to the problem domain. Genetic programming (GP) as an evolutionary computation method can used to reduce the amount of knowledge required to design a CNN for a given problem domain by automatically searching for the optimal architecture. This paper proposes a new algorithm named, GPCNN, which encodes graph-based CNN architectures as trees and uses genetic operators, i.e. mutation, crossover and selection, to find better architectures. A more flexible crossover, partial subtree crossover, is also proposed to improve the search performance. As an preliminary work, GPCNN did not manage to achieve better performance than the state-of-the-art methods due to the limit on computational resource, but it is able to achieve better results than the baseline methods. More importantly, the proposed tree-based graph representation of CNN allows CNN architecture of various shapes, which has a great potential for future work in evolutionary automatic neural architecture search.

Abstract. In recent years, there has been a significant improvement in the detection, identification and classification of objects and images using Convolutional Neural Networks. To study the potential of the Convolutional Neural Network, in this paper three approaches are investigated to train classifiers based on Convolutional Neural Networks. These approaches allow Convolutional Neural Networks to be trained on datasets containing only a few hundred training samples, which results in a successful classification. Two of these approaches are based on the concept of transfer learning. In the first approach features, created by a pretrained Convolutional Neural Network, are used for a classification using a support vector machine. In the second approach a pretrained Convolutional Neural Network gets fine-tuned on a different data set. The third approach includes the design and training for flat Convolutional Neural Networks from the scratch. The evaluation of the proposed approaches is based on a data set provided by the IEEE Geoscience and Remote Sensing Society (GRSS) which contains RGB and LiDAR data of an urban area. In this work it is shown that these Convolutional Neural Networks lead to classification results with high accuracy both on RGB and LiDAR data. Features which are derived by RGB data transferred into LiDAR data by transfer learning lead to better results in classification in contrast to RGB data. Using a neural network which contains fewer layers than common neural networks leads to the best classification results. In this framework, it can furthermore be shown that the practical application of LiDAR images results in a better data basis for classification of vehicles than the use of RGB images.