Deep domain adaptation methods have achieved appealing performance by learning transferable representations from a well-labeled source to different but related unlabeled target domain. Most existing works assume and data share the identical label space, which is often difficult be satisfied in many real-world applications. With emergence of big data, there more practical scenario called partial...

Neural networks have been proved to perform well in network intrusion detection. In order acquire better features of traffic, more learning layers are necessarily required. However, according the results previous research, adding neural might fail improve classification results. fact, after number has reached a certain threshold, performance model tends degrade. this paper, we propose detection...

Single image super-resolution based on convolutional neural networks has been very successful in recent years. However, as the computational cost is too high, making it difficult to apply resource-constrained devices, a big challenge for existing approaches find balance between complexity of CNN model and quality resulting SR. To solve this problem, various lightweight SR have proposed. In pape...

Abstract We propose an Inner-Imaging three-dimensional (3D) attentional feature fusion module for a residual network, which is simple yet effective approach networks. In our attention module, we constructed 3D soft map to refine the input feature. The fuses features from different dimensions, including channel and spatial axes, create map. Then, implemented further fuse features. Lastly, output...