Roads are important mode of transportation, which are very convenient for people’s daily work and life. However, it is challenging to accuratly extract road information from a high-resolution remote sensing image. This paper presents a road extraction method for remote sensing images with a complement UNet (C-UNet). C-UNet contains four modules. Firstly, the standard UNet is used to roughly extract road information from remote sensing images, getting the first segmentation result; secondly, a fixed threshold is utilized to erase partial extracted information; thirdly, a multi-scale dense dilated convolution UNet (MD-UNet) is introduced to discover the complement road areas in the erased masks, obtaining the second segmentation result; and, finally, we fuse the extraction results of the first and the third modules, getting the final segmentation results. Experimental results on the Massachusetts Road dataset indicate that our C-UNet gets the higher results than the state-of-the-art methods, demonstrating its effectiveness.

During image segmentation tasks in computer vision, achieving high accuracy performance while requiring fewer computations and faster inference is a big challenge. This is especially important in medical imaging tasks but one metric is usually compromised for the other. To address this problem, this paper presents an extremely fast, small and computationally effective deep neural network called Stripped-Down UNet (SD-UNet), designed for the segmentation of biomedical data on devices with limited computational resources. By making use of depthwise separable convolutions in the entire network, we design a lightweight deep convolutional neural network architecture inspired by the widely adapted U-Net model. In order to recover the expected performance degradation in the process, we introduce a weight standardization algorithm with the group normalization method. We demonstrate that SD-UNet has three major advantages including: (i) smaller model size (23x smaller than U-Net); (ii) 8x fewer parameters; and (iii) faster inference time with a computational complexity lower than 8M floating point operations (FLOPs). Experiments on the benchmark dataset of the Internatioanl Symposium on Biomedical Imaging (ISBI) challenge for segmentation of neuronal structures in electron microscopic (EM) stacks and the Medical Segmentation Decathlon (MSD) challenge brain tumor segmentation (BRATs) dataset show that the proposed model achieves comparable and sometimes better results compared to the current state-of-the-art.

Kernel fuzzy c-means (KFCM) is a significantly improved version of fuzzy c-means (FCM) for processing linearly inseparable datasets. However, for fuzzification parameter $m=1$, the problem of KFCM (kernel fuzzy c-means) cannot be solved by Lagrangian optimization. To solve this problem, an equivalent model, called kernel probabilistic k-means (KPKM), is proposed here. The novel model relates KFCM to kernel k-means (KKM) in a unified mathematic framework. Moreover, the proposed KPKM can be addressed by the active gradient projection (AGP) method, which is a nonlinear programming technique with constraints of linear equalities and linear inequalities. To accelerate the AGP method, a fast AGP (FAGP) algorithm was designed. The proposed FAGP uses a maximum-step strategy to estimate the step length, and uses an iterative method to update the projection matrix. Experiments demonstrated the effectiveness of the proposed method through a performance comparison of KPKM with KFCM, KKM, FCM and k-means. Experiments showed that the proposed KPKM is able to find nonlinearly separable structures in synthetic datasets. Ten real UCI datasets were used in this study, and KPKM had better clustering performance on at least six datsets. The proposed fast AGP requires less running time than the original AGP, and it reduced running time by 76–95% on real datasets.

Ship target segmentation in infrared scenes has always been a hot topic, since it is an important basis and prerequisite for infrared-guided weapons to reliably capture and recognize ship targets in the sea level background. However, given the small target and fuzzy boundary characteristics of infrared ship images, obtaining accurate pixel-level labels for them is hardly achievable, which brings difficulty to train segmentation networks. To improve the segmentation accuracy of infrared ship images, we propose a two-stage domain adaptation method for infrared ship target segmentation, where the segmentation model is trained using visible ship images with clear target boundaries. In this case, the source domain is the labeled visible ship images, while the target domain is the unlabeled infrared ship images. Specifically, in the first stage, we use an image style transfer network to convert the infrared ship images into those with visible light style, so that the visual disparity between the two domain images can be reduced. Next, the visible, infrared and converted infrared images are input into the Deeplab-v2 segmentation network for training, thereby obtaining the initial network weights. At this time, random attention modules are added separately to the low- and high-level spaces of Deeplab-v2, in order to improve its feature extraction capability. In the second stage, we mix the visible and infrared images through region mixing to acquire the mixed domain images, as well as their corresponding labels. Subsequently, Deeplab-v2 is further trained using the mixed domain images to attain better segmentation accuracy. Experimental results on both the home-made visible-infrared ship image dataset and the public infrared image dataset are superior to those existing mainstream methods, demonstrating its effectiveness.

This paper mainly deals with the problem of short text classification. There are two main contributions. Firstly, we introduce a framework of deep uniform kernel mapping support vector machine (DUKMSVM). The significant merit of this framework is that by expressing the kernel mapping function explicitly with a deep neural network, it is in essence an explicit kernel mapping instead of the traditional kernel function, and it allows better flexibility in dealing with various applications by applying different neural network structures. Secondly, to validate the effectiveness of this framework and to improve the performance of short text classification, we explicitly express the kernel mapping using bidirectional recurrent neural network (BRNN), and propose a deep bidirectional recurrent kernel mapping support vector machine (DRKMSVM) for short text classification. Experimental results on five public short text classification datasets indicate that in terms of classification accuracy, precision, recall rate and F1-score, the DRKMSVM achieves the best performance with the average values of accuracy, precision, recall rate, and F1-score of 87.23%, 86.99%, 86.13% and 86.51% respectively compared to traditional SVM, convolutional neural network (CNN), Naive Bayes (NB), and Deep Neural Mapping Support Vector Machine (DNMSVM) which applies multi-layer perceptron for kernel mapping.