Qian Shi

TL;DR: A deeply supervised (DS) attention metric-based network (DSAMNet) is proposed in this article to learn change maps by means of deep metric learning, in which convolutional block attention modules (CBAM) are integrated to provide more discriminative features.

TL;DR: This article devise an efficient computation offloading mechanism consisting of a delay-aware task graph partition algorithm and an optimal virtual machine selection method in order to minimize an intelligent IoT device's edge resource occupancy and meanwhile satisfy its QoS requirement.

TL;DR: A novel fully convolutional network (FCN), in which a spatial residual inception (SRI) module is proposed to capture and aggregate multi-scale contexts for semantic understanding by successively fusing multi-level features, shows promising potential for building detection from remote sensing images on a large scale.

TL;DR: A novel dual-attention denoising network is proposed that combines two parallel branches to process the spatial and spectral information separately and proves the superiority of the method both visually and quantitatively when compared with state-of-the-art methods.

TL;DR: A multitask deep learning method that simultaneously conducts classification and reconstruction in the open world (named MDL4OW) where unknown classes may exist, and achieves more accurate hyperspectral image classification, especially under the few-shot context.