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.

Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation

Abstract: Semantic segmentation aims to classify every pixel of an input image. Considering the difficulty of acquiring dense labels, researchers have recently been resorting to weak labels to alleviate the annotation burden of segmentation. However, existing works mainly concentrate on expanding the seed of pseudo labels within the image’s salient region. In this work, we propose a non-salient region object mining approach for weakly supervised semantic segmentation. We introduce a graph-based global reasoning unit to strengthen the classification network’s ability to capture global relations among disjoint and distant regions. This helps the network activate the object features outside the salient area. To further mine the non-salient region objects, we propose to exert the segmentation network’s self-correction ability. Specifically, a potential object mining module is proposed to reduce the false-negative rate in pseudo labels. Moreover, we propose a non-salient region masking module for complex images to generate masked pseudo labels. Our non-salient region masking module helps further discover the objects in the non-salient region. Extensive experiments on the PASCAL VOC dataset demonstrate state-of-the-art results compared to current methods. The source codes are available at https://github.com/NUST-Machine-Intelligence-Laboratory/nsrom.

Capping CsPbBr3 with ZnO to improve performance and stability of perovskite memristors

Abstract: The rapid development of information technology has led to an urgent need for devices with fast information storage and processing, a high density, and low energy consumption. Memristors are considered to be next-generation memory devices with all of the aforementioned advantages. Recently, organometallic halide perovskites were reported to be promising active materials for memristors, although they have poor stability and mediocre performance. Herein, we report for the first time the fabrication of stable and high-performance memristors based on inorganic halide perovskite (CsPbBr3, CPB). The devices have electric field-induced bipolar resistive switching (ReS) and memory behaviors with a large on/off ratio (>105), low working voltage ( 104 s), and high environmental stability, which are achieved via ZnO capping within the devices. Such a design can be adapted to various devices. Additionally, the heterojunction between the CPB and ZnO endows the devices with a light-induced ReS effect of more than 103 with a rapid response speed (<1 ms), which enables us to tune the resistance state by changing the light and electric field simultaneously. Such multifunctional devices achieved by the combination of information storage and processing abilities have potential applications for future computing that transcends traditional architectures.