Towards Fine-grained Recognition: Joint Learning for Object Detection and Fine-grained Classification

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.

Fine-grained vehicle classification is the task of classifying make, model, and year of a vehicle. This is a very challenging task, because vehicles of different types but similar color and viewpoint can often look much more similar than vehicles of same type but differing color and viewpoint. Vehicle make, model, and year in combination with vehicle color - are of importance in several applications such as vehicle search, re-identification, tracking, and traffic analysis. In this work we investigate the suitability of several recent landmark convolutional neural network (CNN) architectures, which have shown top results on large scale image classification tasks, for the task of fine-grained classification of vehicles. We compare the performance of the networks VGG16, several ResNets, Inception architectures, the recent DenseNets, and MobileNet. For classification we use the Stanford Cars-196 dataset which features 196 different types of vehicles. We investigate several aspects of CNN training, such as data augmentation and training from scratch vs. fine-tuning. Importantly, we introduce no aspects in the architectures or training process which are specific to vehicle classification. Our final model achieves a state-of-the-art classification accuracy of 94.6% outperforming all related works, even approaches which are specifically tailored for the task, e.g. by including vehicle part detections.

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.

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.

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.

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.

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.

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.

Object detection from UAV thermal infrared images and videos using YOLO models

Convolutional Neural Networks (CNN) have become one of the best algorithms in machine learning for content classification of digital images. The CNN computational complexity is much larger than traditional algorithms, that is why the use of Graphical Processor Units (GPU) and online servers to achieve operations acceleration is a common solution. However, there is a growing demand for real-time processing solutions in the object recognition field mainly implemented on embedded systems, which are limited both in resources and energy consumption. Recently, reported works are focused on minimizing the required resources through two design strategies. The first one is by implementing one accelerator that can be adapted to the operations of the whole CNN. The CNN architecture proposals with one accelerator for each convolution layer belong to the second design strategy, where higher performance is achieved in multiple image processing. A new design strategy is proposed in this paper, which is based on multiple accelerators using a layer operation chaining scheme for computing in parallel the operations corresponding to multiple CNN layers. Three types of parallel data processing are adopted in the proposed architecture, where the parallelism level for convolution layers is determined by defined cost-function-based algorithms. The proposed design strategy is shown by implementing three naive CNNs on a De2i-150 board, in which a peak acceleration of 18.04x was achieved in contrast with state-of-the-art design methods without layer operation chaining. Furthermore, the design results of one modified Alexnet CNN were obtained. According to the obtained results, the proposed design strategy allows to achieve a smaller processing time than that obtained by reported works using the other two design strategies. In addition, a competitive result in resources utilization is obtained for naive CNNs.

Thus far, few studies have been conducted on fine-grained classification tasks for the latest convolutional neural network ConvNeXt, and no effective optimization method has been made available. To achieve more accurate fine-grained classification, this paper proposes two attention embedding methods based on ConvNeXt network and designs a new bilinear CBAM; simultaneously, a multiscale, multi-perspective and all-around attention framework is proposed, which is then applied in ConvNeXt. Experimental verification shows that the accuracy rate of the improved ConvNeXt for fine-grained image classification reaches 87.8%, 91.2%, and 93.2% on fine-grained classification datasets CUB-200-2011, Stanford Cars, and FGVC Aircraft, respectively, showing increases of 2.7%, 0.3% and 0.4%, respectively, compared to those of the original network without optimization, and increases of 3.7%, 8.0% and 2.0%, respectively, compared to those of the traditional BCNN. In addition, ablation experiments are set up to verify the effectiveness of the proposed attention framework.

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.

Introduction. The article considers the solution of the problem of detecting fires at technological facilities in automatic mode. To solve this problem, an approach was chosen to create a convolutional neural network capable of operating on a real-time video stream. Aims and Purposes. The aim of this work is to create a neural network capable of detecting flames and smoke in the image from CCTV cameras. The purposes of the work include: selection of the optimal architecture of the neural network in accordance with the latest research in this field; speeding up the chosen architecture using quantization and filter thinning techniques. Methods. Different architectures of convolutional neural networks performing the task of detecting objects in an image are considered. Their performance and quality of work are compared. The YOLOv5 architecture, its target function, training methods and ways of speeding up work are considered. Results and discu ssion. The paper shows the results of training a convolutional neural network of the YOLOv5 architecture for the task of flame and smoke detection, as well as how the results change when applying neural network acceleration methods. It was determined that the use of such acceleration methods such as quantization and filter cleaning can significantly increase up the speed of the neural network, while almost no loss in accuracy of operation. Conclusions. As a result of the conducted work, the architecture of the neural network was determined for performing the task of detecting a fire source. Based on the chosen architecture, a neural network was trained to detect flames and smoke in the image. The speed of its work allows to process video stream in real-time without using graphic accelerator.