Successful fine-grained image classification methods learn subtle details between visually similar (sub-)classes, but the problem becomes significantly more challenging if the details are missing due to low resolution. Encouraged by the recent success of Convolutional Neural Network (CNN) architectures in image classification, we propose a novel resolution-aware deep model which combines convol...

Deep convolutional neural networks comprise a subclass of deep neural networks (DNN) with a constrained architecture that leverages the spatial and temporal structure of the domain they model. Convolutional networks achieve the best predictive performance in areas such as speech and image recognition by hierarchically composing simple local features into complex models. We try to apply the conv...

We describe how to train a two-layer convolutional Deep Belief Network (DBN) on the 1.6 million tiny images dataset. When training a convolutional DBN, one must decide what to do with the edge pixels of teh images. As the pixels near the edge of an image contribute to the fewest convolutional lter outputs, the model may see it t to tailor its few convolutional lters to better model the edge pix...

Although deep convolutional neural network has been proved to efficiently eliminate coding artifacts caused by the coarse quantization of traditional codec, it’s difficult to train any neural network in front of the encoder for gradient’s back-propagation. In this paper, we propose an end-to-end image compression framework based on convolutional neural network to resolve the problem of non-diff...

Sleep transistors in industrial power-gating designs are custom designed with an optimal size. Consequently, sleep transistor P/G network optimization becomes a problem of finding the optimal number of sleep transistors and their placement as well as optimal P/G network grids, wire widths and layers. This paper presents a fake via based sleep transistor P/G network synthesis method, which addre...

Convolutional neural networks (CNNs) have attracted increasing attention in the remote sensing community. Most CNNs only take the last fully-connected layers as features for the classification of remotely sensed images, discarding the other convolutional layer features which may also be helpful for classification purposes. In this paper, we propose a new adaptive deep pyramid matching (ADPM) mo...

İnternet kullanımının yaygınlaşması ve ağa bağlı cihaz sayısının artması ile siber saldırılarla karşılaşma olasılığı artmaktadır. Siber saldırıların verdiği zararları, engellemek için saldırı tespit sistemleri kullanılmaktadır. Bu çalışmada engellenmesi için, evrişimli sinir ağı kullanılarak özellik seçimine dayalı uygulaması gerçekleştirilmiştir. Eğitim test işlemlerinde CSE-CIC-IDS2018 veri s...

Abstract For refine the regression precision and speed of convolutional neural recognition network, propose improved detection identification algorithm on basis deep learning algorithms, mainly aiming at improving accuracy prediction target recognition. Firstly, acquired images are preprocessed in batches to obtain image datasets with different sizes objects, that is, enhancement small sample i...

This paper proposes perceptual compressive sensing. The network is composed of a fully convolutional measurement and reconstruction network. For the following contributions, the proposed framework is a breakthrough work. Firstly, the fully-convolutional network measures the full image which preserves structure information of the image and removes the block effect. Secondly, with the employment ...