Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction

Predictive analysis on cellular traffic is important for the control and monitoring of wireless networks. Cellular traffic prediction is a challenging problem due to the non- stationarity and dynamic spatial-temporal correlation of the traffic. In this paper, we address the problem of accurate traffic prediction in a base station by proposing a deep neural network called RAConv. Its structure includes residual network, attention mechanism, and deep convolutional network. In the proposed architecture, a deep 3D residual convolutional network (ResConv3D) with three residual blocks are employed to learn the local spatial-temporal features. An attention-aided convolutional long short-term memory network (AConvLSTM) is then used to capture the long-term spatial-temporal dependencies. The use of the attention modules enable the network to focus on the most important spatial-temporal information. We evaluate the performance of the proposed RAConv network using a dataset provided by a Canadian wireless service provider. We consider the traffic prediction on two time scales (i.e., hourly and daily), which exhibit different spatial-temporal dependency patterns. Experimental results show that the proposed RAConv network can achieve accurate prediction under both time scales. Results also show that our proposed network provides a lower root-mean-square error (RMSE) than the conventional ConvLSTM baseline scheme.

Electrochemical machining is a promising non-traditional manufacturing process to make high-quality parts. The benefits of minimal thermally and mechanically induced stresses, free of burr, and a low surface roughness are appealing for industry and research institutes. However, the combined chemical reaction, electric field, fluid mechanics, and material properties involve a significant number of independent parameters which are difficult to analyze in order to draw comprehensive conclusions. To our current knowledge, process responses such as the material removal rate, optimal feed rate, and cutting profile cannot be represented accurately by analytical solutions. In recent years, deep learning has had tremendous success in analyzing sophisticated systems. The improved computation efficiency and reduced size of the training dataset required for deep learning have enabled various prediction models in the manufacturing industry. In this paper, a new approach is developed using the deep convolutional network with the Bayesian optimization algorithm to predict the diameters of the drilled hole from an electrochemical machining process. The Keras application programming interface (API) was used to build the deep convolutional network; the feed rate, pulse-on time, and voltage were used as input parameters to provide a fair comparison with a neural network from previous research. Random dropout layers were added to prevent overfitting of the network. Instead of tuning the network parameter by trial and error, the Bayesian parameter optimization algorithm was implemented to find the optimal set of parameters of the deep convolutional network that yields the minimum mean square error. The proposed algorithm was compared with a previously developed neural network with partially embedded physical knowledge. Improved training speed and accuracy were observed in comparison with the traditional neural network. The prediction model using the proposed deep learning algorithm demonstrated better prediction accuracy and provided a more systematic way to select the hyperparameter for the deep convolutional network.

This paper proposes a method of accurately assessing image quality without a reference image by using a deep convolutional neural network. Existing training based methods usually utilize a compact set of linear filters for learning features of images captured by different sensors to assess their quality. These methods may not be able to learn the semantic features that are intimately related with the features used in human subject assessment. Observing this drawback, this work proposes training a deep convolutional neural network (CNN) with labelled images for image quality assessment. The ReLU in the CNN allows non-linear transformations for extracting high-level image features, providing a more reliable assessment of image quality than linear filters. To enable the neural network to take images of any arbitrary size as input, the spatial pyramid pooling (SPP) is introduced connecting the top convolutional layer and the fully-connected layer. In addition, the SPP makes the CNN robust to object deformations to a certain extent. The proposed method taking an image as input carries out an end-to-end learning process, and outputs the quality of the image. It is tested on public datasets. Experimental results show that it outperforms existing methods by a large margin and can accurately assess the image quality on images taken by different sensors of varying sizes.

Large convolutional networks have achieved impressive classification performances recently. To achieve better performance, convolutional network tends to develop into deeper. However, the increase of network depth causes the linear growth of computational complexity, but cannot bring equivalent increase to the classification accuracy. To alleviate this inconsistence, we propose a cascading approach to accelerate the classification of very deep convolutional neural network. By exploiting the entropy metric to analyze the statistic differences of basic networks between the correctly and mistakenly classified images, we can assign the easily distinguished images to the shallow networks for reducing the computational complexity, and leave the difficultly classified images to the deep networks for maintaining the overall performance. Besides, the proposed cascaded networks can take advantage of the complementarity between different networks, which may boost the classification accuracy compared to the deepest network. We perform the experiments using residual networks of different depths on cifar100 dataset, on the condition of obtaining the similar accuracy to the deepest network, the results show that our cascaded ResNet32-ResNet110 and cascaded ResNet32-ResNet164 can reduce the computation time by 48.6% and 44.3% compared to ResNet110 and ResNet164, respectively. And the cascaded ResNet32-ResNet110-ResNet164 can reduce the computation time by 85.4% compared to the very deep Resnet1001.

Computer-aided diagnosis of ocular disorders like glaucoma can be effectively performed with retinal fundus images. Since the advent of machine learning and later deep learning techniques in medical image analysis, research focusing on automated and early detection of glaucoma has gained prominence. In this paper, we show how a deep Convolutional Neural Network model can be used in visualising the features related to Glaucoma that are consistent with (a subset of) those used by ophthalmologists for diagnosis. However, since the doctors do not necessarily depend entirely on these features but back them up with other important measurements such as visual field testing (HVF), any deep neural network such as CNN may not necessarily be expected to yield 100% accuracy. Further, other important parameters such as Intraocular Pressure (IOP), which may be built into a deep learning model, may not necessarily correlate well with the presence of Glaucoma. In this work, a deep CNN model has been trained and tested on a large number of high-quality fundus images, both normal and glaucomatous. We compare the results with transfer learning models such as VGG16, ResNet50, and MobileNetV2. On an average, we obtained an accuracy of 93.75% in identifying glaucoma, focusing only on the features of the fundus image.

Local binary features for texture classification: Taxonomy and experimental study

Cardiovascular MRI image analysis by using the bio inspired (sand piper optimized) fully deep convolutional network (Bio-FDCN) architecture for an automated detection of cardiac disorders

This paper models unsupervised learning of an identity-based pattern (or copying) in speech called reduplication from raw continuous data with deep convolutional neural networks. We use the ciwGAN architecture (Beguš, 2021a) in which learning of meaningful representations in speech emerges from a requirement that the CNNs generate informative data. We propose a technique to wug-test CNNs trained on speech and, based on four generative tests, argue that the network learns to represent an identity-based pattern in its latent space. By manipulating only two categorical variables in the latent space, we can actively turn an unreduplicated form into a reduplicated form with no other substantial changes to the output in the majority of cases. We also argue that the network extends the identity-based pattern to unobserved data. Exploration of how meaningful representations of identity-based patterns emerge in CNNs and how the latent space variables outside of the training range correlate with identity-based patterns in the output has general implications for neural network interpretability.

COVID-19 virus development has been recognized as a broadly perceived kind of disease. This research work has accomplished several deep convolutional networks (DRN) with pre-training techniques for classifying X-ray chest images into three broad collection, viz., normal or negative, pneumonia positive and COVID-19 positive, based on two other open-source data sets. This fivefold research work is based on data sets consisting of 980 X-ray chest images of contaminated COVID-19 patients, along with experimentation using various deep (Wang et al. in A deep learning algorithm using CT images to screen for COVID-19 virus disease (COVID-19), [10]) learning (Farooq and Hafeez in COVID-ResNet: a deep learning framework for screening of COVID-19 from radiographs, [22]) and neural network methods; organized as primarily it introducing some pre-training techniques that helps the network to learn better, especially in an imbalanced data set, where less cases of COVID-19 are seen along with more cases of other classes. Second, proposing a new and modified convolutional (Wang and Wong in COVID-net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest radiography images, [11]) neural network (MCNN) that is convolutional with the simple application of a filter to an input, which results in activation. Third, repeat the application of the same filter to input entails in a map of activation (viz., feature map), indicates the locations/strength of detected feature in the input; which is an image concatenation of the neural networks and VGG Net networks. Fourth, the computational work reveals that the resulted network achieves the best accuracy by utilizing multiple features extracted by two other robust networks. Fifth, our network evaluation (based on 980 images) reveals that the actual accuracy is surely possible and adaptable in real-life circumstances. At the same time, the average accuracy of our proposed network for detecting COVID-19 cases is 95.60%, with overall average accuracy for all other classes at 82.37%. Finally, a comparative study is to be made with others, in terms of its accuracy, time complexity and high performance and is found to reduce computational cost, by working with large amount of training data which is better than the existing system.KeywordsDetectionClassificationNeural networks (NN)CNNMCNNCOVID-19 virusDWICADImage processingDeep learning (DL)Transfer learningDeep learning feature extractionChest X-ray imagesPrediction

Inferior temporal (IT) cortex in human and nonhuman primates serves visual object recognition. Computational object-vision models, although continually improving, do not yet reach human performance. It is unclear to what extent the internal representations of computational models can explain the IT representation. Here we investigate a wide range of computational model representations (37 in total), testing their categorization performance and their ability to account for the IT representational geometry. The models include well-known neuroscientific object-recognition models (e.g. HMAX, VisNet) along with several models from computer vision (e.g. SIFT, GIST, self-similarity features, and a deep convolutional neural network). We compared the representational dissimilarity matrices (RDMs) of the model representations with the RDMs obtained from human IT (measured with fMRI) and monkey IT (measured with cell recording) for the same set of stimuli (not used in training the models). Better performing models were more similar to IT in that they showed greater clustering of representational patterns by category. In addition, better performing models also more strongly resembled IT in terms of their within-category representational dissimilarities. Representational geometries were significantly correlated between IT and many of the models. However, the categorical clustering observed in IT was largely unexplained by the unsupervised models. The deep convolutional network, which was trained by supervision with over a million category-labeled images, reached the highest categorization performance and also best explained IT, although it did not fully explain the IT data. Combining the features of this model with appropriate weights and adding linear combinations that maximize the margin between animate and inanimate objects and between faces and other objects yielded a representation that fully explained our IT data. Overall, our results suggest that explaining IT requires computational features trained through supervised learning to emphasize the behaviorally important categorical divisions prominently reflected in IT.

To reduce patient's dose, few-view CT reconstruction promises to be a good attempt. The key to better reconstruction is the sparse view artifacts. In recent years, DL(deep learing) has attracted a lot of attention because its outstanding performance in image processing. We propose a deep learning method for few-view CT reconstuction. Our method directly learns an end-to-end mapping between the full-view/few-view reconstruction. The mapping is represented as a deep convolutional neural network (CNN) that takes the few-view reconstruction image as the input and outputs the full-view one. We further show that traditional Dictionary Learning based reconstruction methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art reconstruction quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve trade-offs between performance and speed.

According to the National Highway Traffic Safety Administration, one in ten fatal crashes and two in ten injury crashes were reported as distracted driver accidents in the United State during 2014. In an attempt to mitigate these alarming statistics, this paper explores using a dashboard camera along with computer vision and machine learning to automatically detect distracted drivers. We consider a dataset that incorporates drivers engaging in seven different distracting behaviors using left and/or right hands. Traditional handcrafted features paired with a Support Vector Machine classifier are contrasted with deep Convolutional Neural Networks. The traditional features include a blend of Histogram of Oriented Gradients and Scale-Invariant Feature Transform descriptors used to create Bags of Words. The deep convolutional methods use transfer learning on AlexNet, VGG-16, and ResNet-152. The results yield 85% accuracy with ResNet and 82.5% accuracy with VGG-16, which outperformed AlexNet by almost 10%. Replacing the fully connected layers by a Support Vector Machine classifier did not improve the classification accuracy. The traditional features yielded much lower accuracy than the deep convolutional networks.

Vehicle logo detection based on deep convolutional networks

Deep (machine) learning in recent years has significantly increased the predictive modeling strengths for applications in the areas of computer vision, speech recognition, and natural language processing. Being heavily data-driven, conventional general-purpose deep learning methods mainly rely on training data to learn task-specific data representations. In this thesis, we focus on leveraging novel learning algorithms in deep learning to tackle visual recognition challenges at the three key levels -- namely pixel, object, and image levels. Throughout the thesis, we demonstrate how each and every of our proposed methods can address a specific visual recognition problem. Firstly, we apply deep learning to improve the saliency detection performance of deep networks. A coarse saliency map of the input image's salient object is initially predicted by a convolutional-deconvolutional network (or equivalently a fully convolutional network). Following that, the coarse saliency map is sequentially refined by a separate network called Recurrent Attentional Convolutional-Deconvolutional Network (RACDNN) that shares its network weights across its sequential steps. At every sequential (temporal) step, the same RACDNN is applied to a newly selected/attended image sub-region and it performs saliency map refinement for that particular sub-region. Despite having many learnable network parameters and no access to additional training data, RADCNN can be trained well and it outperforms the "single-step" (coarse saliency detection) baseline and state-of-the-art saliency detection methods by large margins, on several saliency detection benchmark datasets. Secondly, we introduce auto-encoder weight transfer networks (AE-WTN+), a deep model for scaling up object detection. Conventional WTN transfers object class knowledge from the classification weights of a pretrained large-scale image classification network, to the classification weights of an object detection network. However, they suffer from under-fitting and are not able to preserve the rich object class information of novel classes. In this work, we propose a new WTN method -- AE-WTN+ which makes use of normalization techniques to ease network optimization. Inputs and intermediate features are normalized to improve trainability for reduced under-fitting. More importantly, a novel auto-encoding (reconstruction) loss is proposed to encourage information preservation of all classes in the weight predictions of AE-WTN+. This enables the predicted weights of AE-WTN+ to maintain the class discriminability and neighbourhood relationships contained in the pre-trained large-scale classification weights. Experiments on large-scale detection datasets validate the effectiveness of AE-WTN+ on both seen and novel classes. Thirdly, we improve the efficiency of cross-layer network connections for very deep convolutional network in the context of image classification. This gives rise to a new convolutional network architecture called Deluge Networks (DelugeNets) which pass the output (feature activations) of any preceding composite network layer as direct inputs to all succeeding composite layers. For the incoming feature activations of preceding composite layers, the succeeding composite layers first apply rather lightweight cross-layer depthwise convolutional weights on them for feature aggregation. The heavy lifting is carried out by the last convolutional weight layer in each preceding composite layer that performs cross-channel convolutions. The proposed technique enables unimpeded information flow among many layers in very deep DelugeNets with great efficiency. Experiments on small-scale and large-scale datasets show that DelugeNets perform competitively to state-of-the-art deep convolutional networks at lower computational and parameter costs. Fourthly, we propose Stochastic Downsampling (SDPoint), a method to overcome a major limitation suffered by conventional deep convolutional networks -- their computational costs during inference are fixed and cannot be changed. SDPoint downsamples the feature maps at a randomly selected point (layer index) in the network hierarchy during training. The many downsampling configurations known as SDPoint instances each entail a unique downsampling point and downsampling ratio. The same convolutional network weights are shared across the different SDPoint instances that downsample feature maps differently. During inference, the computational cost of a network trained with SDPoint can be instantaneously adjusted to fit a given computational budget, by manually selecting an appropriate SDPoint instance. Additionally, sharing weights between different feature map scales provides significant regularization benefits, making the networks trained with SDPoint less sensitive to scales and more competent. In image classification experiments, SDPoint demonstrates significant cost-accuracy and computational advantages, over independently-trained (non-weight-shared) baselines with various inference costs.

Brain tumor is one of the most aggressive diseases nowadays, resulting in a very short life span if it is diagnosed at an advanced stage. The treatment planning phase is thus essential for enhancing the quality of life for patients. The use of Magnetic Resonance Imaging (MRI) in the diagnosis of brain tumors is extremely widespread, but the manual interpretation of large amounts of images requires considerable effort and is prone to human errors. Hence, an automated method is necessary to identify the most common brain tumors. Convolutional Neural Network (CNN) architectures are successful in image classification due to their high layer count, which enables them to conceive the features effectively on their own. The tuning of CNN hyperparameters is critical in every dataset since it has a significant impact on the efficiency of the training model. Given the high dimensionality and complexity of the data, manual hyperparameter tuning would take an inordinate amount of time, with the possibility of failing to identify the optimal hyperparameters. In this paper, we proposed a Bayesian Optimization-based efficient hyperparameter optimization technique for CNN. This method was evaluated by classifying 3064 T-1-weighted CE-MRI images into three types of brain tumors (Glioma, Meningioma, and Pituitary). Based on Transfer Learning, the performance of five well-recognized deep pre-trained models is compared with that of the optimized CNN. After using Bayesian Optimization, our CNN was able to attain 98.70% validation accuracy at best without data augmentation or cropping lesion techniques, while VGG16, VGG19, ResNet50, InceptionV3, and DenseNet201 achieved 97.08%, 96.43%, 89.29%, 92.86%, and 94.81% validation accuracy, respectively. Moreover, the proposed model outperforms state-of-the-art methods on the CE-MRI dataset, demonstrating the feasibility of automating hyperparameter optimization.