Northwestern Polytechnical University

About: Northwestern Polytechnical University is a education organization based out in Xi'an, China. It is known for research contribution in the topics: Microstructure & Coating. The organization has 47497 authors who have published 56067 publications receiving 657071 citations. The organization is also known as: Xīběi Gōngyè Dàxué & State Northwest Institute of Engineering.

Least Squares Generative Adversarial Networks

Abstract: Unsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process. To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator. We show that minimizing the objective function of LSGAN yields minimizing the Pearson X2 divergence. There are two benefits of LSGANs over regular GANs. First, LSGANs are able to generate higher quality images than regular GANs. Second, LSGANs perform more stable during the learning process. We evaluate LSGANs on LSUN and CIFAR-10 datasets and the experimental results show that the images generated by LSGANs are of better quality than the ones generated by regular GANs. We also conduct two comparison experiments between LSGANs and regular GANs to illustrate the stability of LSGANs.

Least Squares Generative Adversarial Networks

Abstract: Unsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process. To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator. We show that minimizing the objective function of LSGAN yields minimizing the Pearson $\chi^2$ divergence. There are two benefits of LSGANs over regular GANs. First, LSGANs are able to generate higher quality images than regular GANs. Second, LSGANs perform more stable during the learning process. We evaluate LSGANs on five scene datasets and the experimental results show that the images generated by LSGANs are of better quality than the ones generated by regular GANs. We also conduct two comparison experiments between LSGANs and regular GANs to illustrate the stability of LSGANs.

Remote Sensing Image Scene Classification: Benchmark and State of the Art

Abstract: Remote sensing image scene classification plays an important role in a wide range of applications and hence has been receiving remarkable attention. During the past years, significant efforts have been made to develop various datasets or present a variety of approaches for scene classification from remote sensing images. However, a systematic review of the literature concerning datasets and methods for scene classification is still lacking. In addition, almost all existing datasets have a number of limitations, including the small scale of scene classes and the image numbers, the lack of image variations and diversity, and the saturation of accuracy. These limitations severely limit the development of new approaches especially deep learning-based methods. This paper first provides a comprehensive review of the recent progress. Then, we propose a large-scale dataset, termed "NWPU-RESISC45", which is a publicly available benchmark for REmote Sensing Image Scene Classification (RESISC), created by Northwestern Polytechnical University (NWPU). This dataset contains 31,500 images, covering 45 scene classes with 700 images in each class. The proposed NWPU-RESISC45 (i) is large-scale on the scene classes and the total image number, (ii) holds big variations in translation, spatial resolution, viewpoint, object pose, illumination, background, and occlusion, and (iii) has high within-class diversity and between-class similarity. The creation of this dataset will enable the community to develop and evaluate various data-driven algorithms. Finally, several representative methods are evaluated using the proposed dataset and the results are reported as a useful baseline for future research.

Perovskite light-emitting diodes based on spontaneously formed submicrometre-scale structures

Abstract: Light-emitting diodes (LEDs), which convert electricity to light, are widely used in modern society—for example, in lighting, flat-panel displays, medical devices and many other situations. Generally, the efficiency of LEDs is limited by nonradiative recombination (whereby charge carriers recombine without releasing photons) and light trapping1–3. In planar LEDs, such as organic LEDs, around 70 to 80 per cent of the light generated from the emitters is trapped in the device4,5, leaving considerable opportunity for improvements in efficiency. Many methods, including the use of diffraction gratings, low-index grids and buckling patterns, have been used to extract the light trapped in LEDs6–9. However, these methods usually involve complicated fabrication processes and can distort the light-output spectrum and directionality6,7. Here we demonstrate efficient and high-brightness electroluminescence from solution-processed perovskites that spontaneously form submicrometre-scale structures, which can efficiently extract light from the device and retain wavelength- and viewing-angle-independent electroluminescence. These perovskites are formed simply by introducing amino-acid additives into the perovskite precursor solutions. Moreover, the additives can effectively passivate perovskite surface defects and reduce nonradiative recombination. Perovskite LEDs with a peak external quantum efficiency of 20.7 per cent (at a current density of 18 milliamperes per square centimetre) and an energy-conversion efficiency of 12 per cent (at a high current density of 100 milliamperes per square centimetre) can be achieved—values that approach those of the best-performing organic LEDs. The formation of submicrometre-scale structure in perovskite light-emitting diodes can raise their external quantum efficiency beyond 20%, suggesting the possibility of both high efficiency and high brightness.

Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images

Abstract: Object detection in very high resolution optical remote sensing images is a fundamental problem faced for remote sensing image analysis. Due to the advances of powerful feature representations, machine-learning-based object detection is receiving increasing attention. Although numerous feature representations exist, most of them are handcrafted or shallow-learning-based features. As the object detection task becomes more challenging, their description capability becomes limited or even impoverished. More recently, deep learning algorithms, especially convolutional neural networks (CNNs), have shown their much stronger feature representation power in computer vision. Despite the progress made in nature scene images, it is problematic to directly use the CNN feature for object detection in optical remote sensing images because it is difficult to effectively deal with the problem of object rotation variations. To address this problem, this paper proposes a novel and effective approach to learn a rotation-invariant CNN (RICNN) model for advancing the performance of object detection, which is achieved by introducing and learning a new rotation-invariant layer on the basis of the existing CNN architectures. However, different from the training of traditional CNN models that only optimizes the multinomial logistic regression objective, our RICNN model is trained by optimizing a new objective function via imposing a regularization constraint, which explicitly enforces the feature representations of the training samples before and after rotating to be mapped close to each other, hence achieving rotation invariance. To facilitate training, we first train the rotation-invariant layer and then domain-specifically fine-tune the whole RICNN network to further boost the performance. Comprehensive evaluations on a publicly available ten-class object detection data set demonstrate the effectiveness of the proposed method.