Nanjing University of Science and Technology

About: Nanjing University of Science and Technology is a education organization based out in Nanjing, China. It is known for research contribution in the topics: Catalysis & Computer science. The organization has 31581 authors who have published 36390 publications receiving 525474 citations. The organization is also known as: Nánjīng Lǐgōng Dàxué & Nánlǐgōng.

Remedying Defects in Carbon Nitride To Improve both Photooxidation and H2 Generation Efficiencies

Abstract: The outstanding visible light response of carbon nitride has aroused intense expectations regarding its photocatalysis, but it is impeded by the inevitable defects. Here, we report on a facile melamine-based defect-remedying strategy and resultant carbon nitride high-performance photocatalysts (R-C3N4). Melamine with amino groups and a triazine structure was selected as a “little patch” to passivate and remedy various defects inside carbon nitride. Such a remedying effect has been comprehensively proven by Fourier transform infrared spectroscopy (FT-IR), X-ray photoelectron spectroscopy (XPS), transmission electron microscopy (TEM), scanning electron microscopy (SEM), X-ray diffraction (XRD) analyses, and the ninhydrin test. In addition, their effects on photocatalysis were also individually confirmed by chemical methods, including cyano reduction reactions and deamination reactions. Furthermore, melamine remediation can result in g-C3N4/mpg-C3N4 junctions, which also favors electron transfer and charge s...

Privacy-Preserving Federated Learning in Fog Computing

Abstract: Federated learning can combine a large number of scattered user groups and train models collaboratively without uploading data sets, so as to avoid the server collecting user sensitive data. However, the model of federated learning will expose the training set information of users, and the uneven amount of data owned by users in multiple users’ scenarios will lead to the inefficiency of training. In this article, we propose a privacy-preserving federated learning scheme in fog computing. Acting as a participant, each fog node is enabled to collect Internet-of-Things (IoT) device data and complete the learning task in our scheme. Such design effectively improves the low training efficiency and model accuracy caused by the uneven distribution of data and the large gap of computing power. We enable IoT device data to satisfy $\varepsilon $ -differential privacy to resist data attacks and leverage the combination of blinding and Paillier homomorphic encryption against model attacks, which realize the security aggregation of model parameters. In addition, we formally verified our scheme can not only guarantee both data security and model security but completely resist collusion attacks launched by multiple malicious entities. Our experiments based on the Fashion-MNIST data set prove that our scheme is highly efficient in practice.

Causal Intervention for Weakly-Supervised Semantic Segmentation

Abstract: We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only image-level labels -- the most crucial step in WSSS. We attribute the cause of the ambiguous boundaries of pseudo-masks to the confounding context, e.g., the correct image-level classification of "horse" and "person" may be not only due to the recognition of each instance, but also their co-occurrence context, making the model inspection (e.g., CAM) hard to distinguish between the boundaries. Inspired by this, we propose a structural causal model to analyze the causalities among images, contexts, and class labels. Based on it, we develop a new method: Context Adjustment (CONTA), to remove the confounding bias in image-level classification and thus provide better pseudo-masks as ground-truth for the subsequent segmentation model. On PASCAL VOC 2012 and MS-COCO, we show that CONTA boosts various popular WSSS methods to new state-of-the-arts.