Application of projection pursuit learning to boundary detection and deblurring in images

Projection pursuit learning networks (PPLNs) have been used in many fields of research but have not been widely used in image processing. In this paper we demonstrate how this highly promising technique may be used to connect edges and produce continuous boundaries. We also propose the application of PPLN to deblurring a degraded image when little or no a priori information about the blur is available. The PPLN was successful at developing an inverse blur filter to enhance blurry images. Theory and background information on projection pursuit regression (PPR) and PPLN are also presented.     

Immunity-based hybrid learning methods for approximator structure and parameter adjustment

From the point of view of information processing the immune system is a highly parallel and distributed intelligent system which has learning, memory, and associative retrieval capabilities. In this paper we present two immunity-based hybrid learning approaches for function approximation (or regression) problems that involve adjusting the structure and parameters of spatially localized models (e.g., radial basis function networks). The number and centers of the receptive fields for local models are specified by immunity-based structure adaptation algorithms, while the parameters of the local models, which enter in a linear fashion, are tuned separately using a least-squares method. The effectiveness of the procedure is demonstrated through a nonlinear function approximation problem and a nonlinear dynamical system modeling problem.     

A fuzzy Actor-Critic reinforcement learning network

One of the difficulties encountered in the application of reinforcement learning methods to real-world problems is their limited ability to cope with large-scale or continuous spaces. In order to solve the curse of the dimensionality problem, resulting from making continuous state or action spaces discrete, a new fuzzy Actor-Critic reinforcement learning network (FACRLN) based on a fuzzy radial basis function (FRBF) neural network is proposed. The architecture of FACRLN is realized by a four-layer FRBF neural network that is used to approximate both the action value function of the Actor and the state value function of the Critic simultaneously. The Actor and the Critic networks share the input, rule and normalized layers of the FRBF network, which can reduce the demands for storage space from the learning system and avoid repeated computations for the outputs of the rule units. Moreover, the FRBF network is able to adjust its structure and parameters in an adaptive way with a novel self-organizing approach according to the complexity of the task and the progress in learning, which ensures an economic size of the network. Experimental studies concerning a cart-pole balancing control illustrate the performance and applicability of the proposed FACRLN.     

Multi layer ELM-RBF for multi-label learning

Many neural network methods such as ML-RBF and BP-MLL have been used for multi-label classification. Recently, extreme learning machine (ELM) is used as the basic elements to handle multi-label classification problem because of its fast training time. Extreme learning machine based auto encoder (ELM-AE) is a novel method of neural network which can reproduce the input signal as well as auto encoder, but it can not solve the over-fitting problem in neural networks elegantly. Introducing weight uncertainty into ELM-AE, we can treat the input weights as random variables following Gaussian distribution and propose weight uncertainty ELM-AE (WuELM-AE). In this paper, a neural network named multi layer ELM-RBF for multi-label learning (ML-ELM-RBF) is proposed. It is derived from radial basis function for multi-label learning (ML-RBF) and WuELM-AE. ML-ELM-RBF firstly stacks WuELM-AE to create a deep network, and then it conducts clustering analysis on samples features of each possible class to compose the last hidden layer. ML-ELM-RBF has achieved satisfactory results on single-label and multi-label data sets. Experimental results show that WuELM-AE and ML-ELM-RBF are effective learning algorithms.     

Neural networks for finite constraint satisfaction

Constraint Satisfaction Problems (CSPs) are in general NP-hard, and a general deterministic polynomial time algorithm is not known. They play a central role in real-life problems. The satisfaction of a Conjunctive Normal Form (CNF-SAT)is the core of any CSP. We present a new modelisation technique for any CSP with finite variable domains, and, in particular, for solving CNF-SAT. The knowledge representation is based on two fundamental types of constraint: the choice constraint, and the exclusion constraint. These models are then implemented by means of several different neural networks, some based on backpropagation learning and others on different procedures. All these networks are trained through a supervised procedure, and learn to efficiently solve CNF-SAT. The results of significant tests are described: they show that some networks can effectively solve the proposed problems.     

MFF-GAN: An unsupervised generative adversarial network with adaptive and gradient joint constraints for multi-focus image fusion

Multi-focus image fusion is an enhancement method to generate full-clear images, which can address the depth-of-field limitation in imaging of optical lenses. Most existing methods generate the decision map to realize multi-focus image fusion, which usually lead to detail loss due to misclassification, especially near the boundary line of the focused and defocused regions. To overcome this challenge, this paper presents a new generative adversarial network with adaptive and gradient joint constraints to fuse multi-focus images. In our model, an adaptive decision block is introduced to determine whether source pixels are focused or not based on the difference of repeated blur. Under its guidance, a specifically designed content loss can dynamically guide the optimization trend, that is, force the generator to produce a fused result of the same distribution as the focused source images. To further enhance the texture details, we establish an adversarial game so that the gradient map of the fused result approximates the joint gradient map constructed based on the source images. Our model is unsupervised without requiring ground-truth fused images for training. In addition, we release a new dataset containing 120 high-quality multi-focus image pairs for benchmark evaluation. Experimental results demonstrate the superiority of our method over the state-of-the-art in terms of both subjective visual effect and quantitative metrics. Moreover, our method is about one order of magnitude faster compared with the state-of-the-art.     

An algorithm for semi-supervised learning in image retrieval

We study the problem of image retrieval based on semi-supervised learning. Semi-supervised learning has attracted a lot of attention in recent years. Different from traditional supervised learning. Semi-supervised learning makes use of both labeled and unlabeled data. In image retrieval, collecting labeled examples costs human efforts, while vast amounts of unlabeled data are often readily available and offer some additional information. In this paper, based on support vector machine (SVM), we introduce a semi-supervised learning method for image retrieval. The basic consideration of the method is that, if two data points are close to each, they should share the same label. Therefore, it is reasonable to search a projection with maximal margin and locality preserving property. We compare our method to standard SVM and transductive SVM. Experimental results show efficiency and effectiveness of our method.     

MIMLRBF: RBF neural networks for multi-instance multi-label learning

In multi-instance multi-label learning (MIML), each example is not only represented by multiple instances but also associated with multiple class labels. Several learning frameworks, such as the traditional supervised learning, can be regarded as degenerated versions of MIML. Therefore, an intuitive way to solve MIML problem is to identify its equivalence in its degenerated versions. However, this identification process would make useful information encoded in training examples get lost and thus impair the learning algorithm's performance. In this paper, RBF neural networks are adapted to learn from MIML examples. Connections between instances and labels are directly exploited in the process of first layer clustering and second layer optimization. The proposed method demonstrates superior performance on two real-world MIML tasks.     

A hybrid of transformer and CNN for efficient single image super-resolution via multi-level distillation

In recent years, single image super-resolution (SISR) models based on convolutional neural networks (CNN) have made significant progress and have gradually become the mainstream method. However, they still suffer from high computational costs, heavy memory consumption, and a limited receptive field. Although Vision Transformer has a stronger modeling capability and larger receptive field, it also incurs high computing power consumption and memory occupation. To address these issues, we propose a hybrid network of Transformer and CNN with cascaded feature distillation blocks for efficient image super-resolution (TCFDN), which can take advantage of both local information and long-term interactions while being flexible enough. Concretely, TCFDN consists of cascaded Transformer-CNN feature distillation blocks (TCFDB) and an upsampling module. The feature distillation pipeline of TCFDB can help our model gradually learn refined features with better representation ability while remaining lightweight. Besides, we also designed an enhanced Swin Transformer layer (ESTL) by replacing the multi-layer perceptron (MLP) in the standard Transformer with a convolutional feed-forward layer (CFF), which is more suitable for SR tasks. Then, the enhanced spatial attention embedded in TCFDB can boost SR performance further. Moreover, we observe that using a more advanced loss function, i.e., the contrastive loss, can also bring a PSNR gain of 0.01 dB–0.03 dB on public benchmarks. Extensive experiments demonstrate that TCFDN outperforms the state-of-the-art methods in terms of a better trade-off between performance and model size. Under the 4X SR task on the public benchmark Urban100, our TCFDN outperforms the second-best model by 0.37 dB in terms of PSNR. Compared with other state-of-the-art methods, the total number of parameters in TCFDN can be reduced by up to 32 % while maintaining competitive performance.     

A forecasting system for car fuel consumption using a radial basis function neural network

A predictive system for car fuel consumption using a radial basis function (RBF) neural network is proposed in this paper. The proposed work consists of three parts: information acquisition, fuel consumption forecasting algorithm and performance evaluation. Although there are many factors affecting the fuel consumption of a car in a practical drive procedure, in the present system the relevant factors for fuel consumption are simply decided as make of car, engine style, weight of car, vehicle type and transmission system type which are used as input information for the neural network training and fuel consumption forecasting procedure. In fuel consumption forecasting, to verify the effect of the proposed RBF neural network predictive system, an artificial neural network with a back-propagation (BP) neural network is compared with an RBF neural network for car fuel consumption prediction. The prediction results demonstrated the proposed system using the neural network is effective and the performance is satisfactory in terms of fuel consumption prediction.