Currently, the different deep neural network (DNN) learning approaches have done much for the classification of hyperspectral images (HSIs), especially most of them use the convolutional neural ...network (CNN). HSI data have the characteristics of multidimensionality, correlation, nonlinearity, and a large amount of data. Therefore, it is particularly important to extract deeper features in HSIs by reducing dimensionalities which help improve the classification in both spectral and spatial domains. In this article, we present a spatial-spectral HSI classification algorithm, local similarity projection Gabor filtering (LSPGF), which uses local similarity projection (LSP)-based reduced dimensional CNN with a 2-D Gabor filtering algorithm. First, use the local similarity analysis to reduce the dimensionality of the hyperspectral data, and then we use the 2-D Gabor filter to filter the reduced hyperspectral data to generate spatial tunnel information. Second, use the CNN to extract features from the original hyperspectral data to generate spectral tunnel information. Third, the spatial tunnel information and the spectral tunnel information are fused to form the spatial-spectral feature information, which is input into the deep CNN to extract more effective features; and finally, a dual optimization classifier is used to classify the final extracted features. This article compares the performance of the proposed method with other algorithms in three public HSI databases and shows that the overall accuracy of the classification of LSPGF outperforms all datasets.
Neural Style Transfer: A Review Jing, Yongcheng; Yang, Yezhou; Feng, Zunlei ...
IEEE transactions on visualization and computer graphics,
2020-Nov.-1, 2020-11-00, 2020-11-1, 20201101, Letnik:
26, Številka:
11
Journal Article
Recenzirano
The seminal work of Gatys et al. demonstrated the power of Convolutional Neural Networks (CNNs) in creating artistic imagery by separating and recombining image content and style. This process of ...using CNNs to render a content image in different styles is referred to as Neural Style Transfer (NST). Since then, NST has become a trending topic both in academic literature and industrial applications. It is receiving increasing attention and a variety of approaches are proposed to either improve or extend the original NST algorithm. In this paper, we aim to provide a comprehensive overview of the current progress towards NST. We first propose a taxonomy of current algorithms in the field of NST. Then, we present several evaluation methods and compare different NST algorithms both qualitatively and quantitatively. The review concludes with a discussion of various applications of NST and open problems for future research. A list of papers discussed in this review, corresponding codes, pre-trained models and more comparison results are publicly available at: https://osf.io/f8tu4/ .
Evolutionary paradigms have been successfully applied to neural network designs for two decades. Unfortunately, these methods cannot scale well to the modern deep neural networks due to the ...complicated architectures and large quantities of connection weights. In this paper, we propose a new method using genetic algorithms for evolving the architectures and connection weight initialization values of a deep convolutional neural network to address image classification problems. In the proposed algorithm, an efficient variable-length gene encoding strategy is designed to represent the different building blocks and the potentially optimal depth in convolutional neural networks. In addition, a new representation scheme is developed for effectively initializing connection weights of deep convolutional neural networks, which is expected to avoid networks getting stuck into local minimum that is typically a major issue in the backward gradient-based optimization. Furthermore, a novel fitness evaluation method is proposed to speed up the heuristic search with substantially less computational resource. The proposed algorithm is examined and compared with 22 existing algorithms on nine widely used image classification tasks, including the state-of-the-art methods. The experimental results demonstrate the remarkable superiority of the proposed algorithm over the state-of-the-art designs in terms of classification error rate and the number of parameters (weights).
Weakly Supervised Object Detection (WSOD), using only image-level annotations to train object detectors, is of growing importance in object recognition. In this paper, we propose a novel deep network ...for WSOD. Unlike previous networks that transfer the object detection problem to an image classification problem using Multiple Instance Learning (MIL), our strategy generates proposal clusters to learn refined instance classifiers by an iterative process. The proposals in the same cluster are spatially adjacent and associated with the same object. This prevents the network from concentrating too much on parts of objects instead of whole objects. We first show that instances can be assigned object or background labels directly based on proposal clusters for instance classifier refinement, and then show that treating each cluster as a small new bag yields fewer ambiguities than the directly assigning label method. The iterative instance classifier refinement is implemented online using multiple streams in convolutional neural networks, where the first is an MIL network and the others are for instance classifier refinement supervised by the preceding one. Experiments are conducted on the PASCAL VOC, ImageNet detection, and MS-COCO benchmarks for WSOD. Results show that our method outperforms the previous state of the art significantly.
Rapidly random-exploring tree (RRT) and its variants are very popular due to their ability to quickly and efficiently explore the state space. However, they suffer sensitivity to the initial solution ...and slow convergence to the optimal solution, which means that they consume a lot of memory and time to find the optimal path. It is critical to quickly find a short path in many applications such as the autonomous vehicle with limited power/fuel. To overcome these limitations, we propose a novel optimal path planning algorithm based on the convolutional neural network (CNN), namely the neural RRT* (NRRT*). The NRRT* utilizes a nonuniform sampling distribution generated from a CNN model. The model is trained using quantities of successful path planning cases. In this article, we use the A* algorithm to generate the training data set consisting of the map information and the optimal path. For a given task, the proposed CNN model can predict the probability distribution of the optimal path on the map, which is used to guide the sampling process. The time cost and memory usage of the planned path are selected as the metric to demonstrate the effectiveness and efficiency of the NRRT*. The simulation results reveal that the NRRT* can achieve convincing performance compared with the state-of-the-art path planning algorithms. Note to Practitioners -The motivation of this article stems from the need to develop a fast and efficient path planning algorithm for practical applications such as autonomous driving, warehouse robot, and countless others. Sampling-based algorithms are widely used in these areas due to their good scalability and high efficiency. However, the quality of the initial path is not guaranteed and it takes much time to converge to the optimal path. To quickly obtain a high-quality initial path and accelerate the convergence speed, we propose the NRRT*. It utilizes a nonuniform sampling distribution and achieves better performance. The NRRT* can be also applied to other sampling-based algorithms for improved results in different applications.
Densely Residual Laplacian Super-Resolution Anwar, Saeed; Barnes, Nick
IEEE transactions on pattern analysis and machine intelligence,
2022-March-1, 2022-Mar, 2022-3-1, 20220301, Letnik:
44, Številka:
3
Journal Article
Recenzirano
Super-Resolution convolutional neural networks have recently demonstrated high-quality restoration for single images. However, existing algorithms often require very deep architectures and long ...training times. Furthermore, current convolutional neural networks for super-resolution are unable to exploit features at multiple scales and weigh them equally or at only static scale only, limiting their learning capability. In this exposition, we present a compact and accurate super-resolution algorithm, namely, densely residual laplacian network (DRLN). The proposed network employs cascading residual on the residual structure to allow the flow of low-frequency information to focus on learning high and mid-level features. In addition, deep supervision is achieved via the densely concatenated residual blocks settings, which also helps in learning from high-level complex features. Moreover, we propose Laplacian attention to model the crucial features to learn the inter and intra-level dependencies between the feature maps. Furthermore, comprehensive quantitative and qualitative evaluations on low-resolution, noisy low-resolution, and real historical image benchmark datasets illustrate that our DRLN algorithm performs favorably against the state-of-the-art methods visually and accurately.
Automated Lymph Node (LN) detection is an important clinical diagnostic task but very challenging due to the low contrast of surrounding structures in Computed Tomography (CT) and to their varying ...sizes, poses, shapes and sparsely distributed locations. State-of-the-art studies show the performance range of 52.9% sensitivity at 3.1 false-positives per volume (FP/vol.), or 60.9% at 6.1 FP/vol. for mediastinal LN, by one-shot boosting on 3D HAAR features. In this paper, we first operate a preliminary candidate generation stage, towards -100% sensitivity at the cost of high FP levels (-40 per patient), to harvest volumes of interest (VOI). Our 2.5D approach consequently decomposes any 3D VOI by resampling 2D reformatted orthogonal views N times, via scale, random translations, and rotations with respect to the VOI centroid coordinates. These random views are then used to train a deep Convolutional Neural Network (CNN) classifier. In testing, the CNN is employed to assign LN probabilities for all N random views that can be simply averaged (as a set) to compute the final classification probability per VOI. We validate the approach on two datasets: 90 CT volumes with 388 mediastinal LNs and 86 patients with 595 abdominal LNs. We achieve sensitivities of 70%/83% at 3 FP/vol. and 84%/90% at 6 FP/vol. in mediastinum and abdomen respectively, which drastically improves over the previous state-of-the-art work.
As an important task in the field of remote sensing image processing, remote sensing image change detection (CD) has made significant advances through the use of convolutional neural networks (CNN). ...The Transformer has recently been introduced into the field of CD due to its excellent global perception capabilities. Some works have attempted to combine CNN and Transformer to jointly harvest local-global features. However, these works have not paid much attention to the interaction between the features extracted by both. Also, the use of the Transformer has resulted in significant resource consumption. In this paper, we propose the Asymmetric Cross-attention Hierarchical Network (ACAHNet) by combining CNN and Transformer in a series-parallel manners. The proposed Asymmetric Multi-headed Cross Attention (AMCA) module reduces the quadratic computational complexity of the Transformer to linear, and the module enhances the interaction between features extracted from the CNN and the Transformer. Different from the early and late fusion strategies employed in previous work, the effectiveness of the mid-term fusion strategy employed by ACAHNet shows a new choice of timing for feature fusion in the CD task. Our experiments on the proposed method on three public datasets show that our network has better performance in terms of effectiveness and computational resource consumption compared to other comparative methods.
This article proposes an end-to-end method based on an improved convolutional neural network model for inverter fault diagnosis. First, transient time-domain sequence data under different faults are ...analyzed, and raw signals are taken as fault representations without manually selecting feature extraction methods. Second, the model can automatically learn and extract features in the input domain using stacked convolution layers with the wide first-layer convolution kernel and a global max pooling layer; thus, it eliminated the influence of expert experience. Finally, the fault diagnosis results of the three-phase voltage-source inverter are automatically obtained in the softmax layer. The proposed fault diagnosis method has superior recognition performance with mixed noise data and variable load data. Contrastive experiments show that the improved fault diagnosis model is effective than traditional machine learning and other deep learning methods.