检索结果-内蒙古大学图书馆

Residual objectness for imbalance reduction

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chen, Joya Liu, Dong Luo, Bin Peng, Xuezheng Xu, Tong Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Tencent TaiQ Team

For a long time, object detectors have suffered from extreme imbalance between foregrounds and backgrounds. While several sampling/reweighting schemes have been explored to alleviate the imbalance, they are usually heuristic and demand laborious hyper-parameters tuning, which is hard to achieve the optimality. In this paper, we first reveal that such the imbalance could be addressed in a learning-based manner. Guided by this illuminating observation, we propose a novel Residual Objectness (ResObj) mechanism that addresses the imbalance by end-to-end optimization, while no further hand-crafted sampling/reweighting is required. Specifically, by applying multiple cascaded objectness-related modules with residual connections, we formulate an elegant consecutive refinement procedure for distinguishing the foregrounds from backgrounds, thereby progressively addressing the imbalance. Extensive experiments present the effectiveness of our method, as well as its compatibility and adaptivity for both region-based and one-stage detectors, namely, the RetinaNet-ResObj, YOLOv3-ResObj and FasterRCNN-ResObj achieve relative 3.6%, 3.9%, 3.2% Average Precision (AP) improvements compared with their vanilla models on COCO, respectively. Copyright © 2019, The Authors. All rights reserved.

关键词： Object detection

Semantic-Preserving Abstractive Text Summarization with Siamese Generative Adversarial Net

学校读者我要写书评

暂无评论

Semantic-Preserving Abstractive Text Summarization with Siam...

2022 Findings of the Association for Computational Linguistics: NAACL 2022

作者： Sheng, Xin Xu, Linli Xu, Yinlong Jiang, Deqiang Ren, Bo School of Computer Science and Technology University of Science and Technology of China. China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China IFLYTEK Co. Ltd. China Tencent Youtu Lab China

ISBN: (纸本)9781955917766

We propose a novel siamese generative adversarial net for abstractive text summarization (SSPGAN), which can preserve the main semantics of the source text. Different from previous generative adversarial net based methods, SSPGAN is equipped with a siamese semanticpreserving discriminator, which can not only be trained to discriminate the machine-generated summaries from the human-summarized ones, but also ensure the semantic consistency between the source text and target summary. As a consequence of the min-max game between the generator and the siamese semantic-preserving discriminator, the generator can generate a summary that conveys the key content of the source text more accurately. Extensive experiments on several text summarization benchmarks in different languages demonstrate the effectiveness of the proposed method. © Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.

关键词： Semantics

USER: A unified information search and recommendation model based on integrated behavior sequence

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yao, Jing Dou, Zhicheng Xie, Ruobing Lu, Yanxiong Wang, Zhiping Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China WeChat Search Application Department Tencent China Beijing Key Laboratory of Big Data Management and Analysis Methods Key Laboratory of Data Engineering and Knowledge Engineering MOE

Search and recommendation are the two most common approaches used by people to obtain information. They share the same goal - satisfying the user's information need at the right time. There are already a lot of Internet platforms and Apps providing both search and recommendation services, showing us the demand and opportunity to simultaneously handle both tasks. However, most platforms consider these two tasks independently - they tend to train separate search model and recommendation model, without exploiting the relatedness and dependency between them. In this paper, we argue that jointly modeling these two tasks will benefit both of them and finally improve overall user satisfaction. We investigate the interactions between these two tasks in the specific information content service domain. We propose first integrating the user's behaviors in search and recommendation into a heterogeneous behavior sequence, then utilizing a joint model for handling both tasks based on the unified sequence. More specifically, we design the Unified Information SEarch and Recommendation model (USER), which mines user interests from the integrated sequence and accomplish the two tasks in a unified way. Experiments on a dataset from a real-world information content service platform verify that our model outperforms separate search and recommendation baselines. Copyright © 2021, The Authors. All rights reserved.

关键词： Recommender systems

Queue Length Prediction Method of Short-linked Intersections Based on Long Short-Term Memory 9

学校读者我要写书评

暂无评论

Queue Length Prediction Method of Short-linked Intersections...

9th International Conference on Systems and Informatics, ICSAI 2023

作者： Shi, Kang Shi, Kang Yang, Jun Liang, Zi Jun Jun Liang, Zi Li, Yu Qi Wang, Rui Han Tongji University Key Laboratory of Road and Traffic Engineering Ministry of Education Shanghai201804 China Anhui Chaoyuan Information Technology Co. Ltd HeFei230088 China Anhui Province Transportation Big Data Analysis and Application Engineering Laboratory Hefei230601 China Hefei University School of Urban Construction and Transportation Hefei230601 China

ISBN: (纸本)9798350383706

To address traffic congestion and vehicle queue overflow at short-link intersections, it is essential to conduct a predictive analysis of vehicle queue length between these intersections. This helps in proactively implementing appropriate traffic management measures to prevent traffic overflow and congestion. In this paper, we propose a short-link intersection vehicle queue length prediction method based on Long Short-Term Memory (LSTM). First, historical traffic data from the morning peak hours over the past month is collected. After comparing multiple machine learning models, LSTM is chosen for traffic flow prediction. Subsequently, mathematical models are used to predict queue length at future time intervals. Through practical validation, we found that the proposed method for predicting queue length between short-link intersections in this paper is effective, with an average prediction error rate of 11.9%. It meets the requirements for predicting vehicle queue length between intersections and proactively controlling them, holding significant practical significance for preventing traffic flow and congestion events. © 2023 IEEE.

关键词： Long short-term memory

Low-Temperature Growing Anatase TiO2/SnO2 Multi-dimensional Heterojunctions at MXene Conductive Network for High-Efficient Perovskite Solar Cells

学校读者我要写书评

暂无评论

Nano-Micro Letters 2020年第3期12卷 199-217页

作者： Linsheng Huang Xiaowen Zhou Rui Xue Pengfei Xu Siliang Wang Chao Xu Wei Zeng Yi Xiong Hongqian Sang Dong Liang National Engineering Research Center for Agro‑Ecological Big Data Analysis and Application School of Electronics and Information EngineeringAnhui UniversityNo.111 Jiulong RoadHefei 230601People’s Republic of China Science and Technology Institute Hubei Key Laboratory of Biomass Fibers and Eco‑Dyeing and FinishingWuhan Textile UniversityWuhan 430073People’s Republic of China School of Physics and Technology MOE Key Laboratory of Artificial Micro‑and Nano‑Structures and Center for Electron MicroscopyWuhan UniversityWuhan 430072People’s Republic of China Department of Physics King’s College LondonThe StrandLondon WC2R 2LSUK

A multi-dimensional conductive heterojunction structure,composited by TiO2,SnO2,and Ti3C2TX MXene,is facilely designed and applied as electron transport layer in efficient and stable planar perovskite solar *** on an oxygen vacancy scramble effect,the zero-dimensional anatase TiO2 quantum dots,surrounding on two-dimensional conductive Ti3C2TX sheets,are in situ rooted on three-dimensional SnO2 nanoparticles,constructing nanoscale TiO2/SnO2 *** fabrication is implemented in a controlled lowtemperature anneal method in air and then in N2 *** the optimal MXene content,the optical property,the crystallinity of perovskite layer,and internal interfaces are all facilitated,contributing more amount of carrier with effective and rapid transferring in *** champion power conversion efficiency of resultant perovskite solar cells achieves 19.14%,yet that of counterpart is just 16.83%.In addition,it can also maintain almost 85%of its initial performance for more than 45 days in 30–40%humidity air;comparatively,the counterpart declines to just below 75%of its initial performance.

关键词： In situ fabrication Multi-dimensional heterojunction Oxygen vacancy scramble effect Electron transport layer Perovskite solar cells

Disentangling Heterogeneous Knowledge Concept Embedding for Cognitive Diagnosis on Untested Knowledge

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Miao Wang, Ziming Xing, Runtian Xiao, Kui Li, Zhifei Zhang, Yan Tang, Chang School of Computer Science and Information Engineering Hubei University China Key Laboratory of Intelligent Sensing System and Security China Hubei Key Laboratory of Big Data Intelligent Analysis and Application China

Cognitive diagnosis is a fundamental and critical task in learning assessment, which aims to infer students’ proficiency on knowledge concepts from their response logs. Current works assume each knowledge concept will certainly be tested and covered by multiple exercises. However, whether online or offline courses, it’s hardly feasible to completely cover all knowledge concepts in several exercises. Restricted tests lead to undiscovered knowledge deficits, especially untested knowledge concepts(UKCs). In this paper, we propose a novel framework for Cognitive Diagnosis called Disentangling Heterogeneous Knowledge Cognitive Diagnosis(DisKCD) on untested knowledge. Specifically, we leverage course grades, exercise questions, and learning resources to learn the potential representations of students, exercises, and knowledge concepts. In particular, knowledge concepts are disentangled into tested and untested based on the limiting actual exercises. We construct a heterogeneous relation graph network via students, exercises, tested knowledge concepts(TKCs), and UKCs. Then, through a hierarchical heterogeneous message-passing mechanism, the fine-grained relations are incorporated into the embeddings of the entities. Finally, the embeddings will be applied to multiple existing cognitive diagnosis models to infer students’ proficiency on UKCs. Experimental results on real-world datasets show that the proposed model can effectively improve the performance of the task of diagnosing students’ proficiency on UKCs. Our code is available at https://***/Hubuers/DisKCD. © 2024, CC BY.

关键词： Students

Faster distributed deep net training: Computation and communication decoupled stochastic gradient descent

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Shen, Shuheng Xu, Linli Liu, Jingchang Liang, Xianfeng Cheng, Yifei Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China School of Data Science University of Science and Technology of China

With the increase in the amount of data and the expansion of model scale, distributed parallel training becomes an important and successful technique to address the optimization challenges. Nevertheless, although distributed stochastic gradient descent (SGD) algorithms can achieve a linear iteration speedup, they are limited significantly in practice by the communication cost, making it difficult to achieve a linear time speedup. In this paper, we propose a computation and communication decoupled stochastic gradient descent (CoCoDSGD) algorithm to run computation and communication in parallel to reduce the communication cost. We prove that CoCoD-SGD has a linear iteration speedup with respect to the total computation capability of the hardware resources. In addition, it has a lower communication complexity and better time speedup comparing with traditional distributed SGD algorithms. Experiments on deep neural network training demonstrate the significant improvements of CoCoD-SGD: when training ResNet18 and VGG16 with 16 Geforce GTX 1080Ti GPUs, CoCoD-SGD is up to 2-3x faster than traditional synchronous SGD. Copyright © 2019, The Authors. All rights reserved.

关键词： Program processors

Individual tree detection and counting based on high-resolution imagery and the canopy height model data

学校读者我要写书评

暂无评论

地球空间信息科学学报（英文版） 2024年第6期27卷中插23,2162-2178页

作者： Ye Zhang Moyang Wang Joseph Mango Liang Xin Chen Meng Xiang Li Key Laboratory of Geographic Information Science(Ministry of Education)and School of Geographic Sciences East China Normal UniversityShanghaiChina Department of Transportation and Geotechnical Engineering University of Dar es SalaamDar es salaamTanzania College of Surveying and Geographic Informatics Tongji UniversityShanghaiChina Cadre School of Shanghai Municipal Bureau of Planning and Natural Resources ShanghaiChina School of Ecology and Environmental Sciences East China Normal UniversityShanghaiChina Key Laboratory of Geographic Information Science(Ministry of Education)and School of Geographic Sciences East China Normal UniversityShanghaiChina Shanghai Key Lab for Urban Ecological Processes and Eco-Restoration East China Normal UniversityShanghaiChina Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities(Ministry of Natural Resources) East China Normal UniversityShanghaiChina

Individual Tree Detection-and-Counting(ITDC)is among the important tasks in town areas,and numerous methods are proposed in this *** their many advantages,still,the proposed methods are inadequate to provide robust results because they mostly rely on the direct field *** paper presents a novel approach involving high-resolution imagery and the Canopy-Height-Model(CHM)data to solve the ITDC *** new approach is studied in six urban scenes:farmland,woodland,park,industrial land,road and residential ***,it identifies tree canopy regions using a deep learning network from high-resolution *** then deploys the CHM-data to detect treetops of the canopy regions using a local maximum algorithm and individual tree canopies using the region ***,it calculates and describes the number of individual trees and tree *** proposed approach is experimented with the data from Shanghai,*** results show that the individual tree detection method had an average overall accuracy of 0.953,with a precision of 0.987 for woodland ***,the R2 value for canopy segmentation in different urban scenes is greater than 0.780 and 0.779 for canopy area and diameter size,*** results confirm that the proposed method is robust enough for urban tree planning and management.

关键词： Individual tree detection-and-counting(ITDC) deep learning high-resolution imagery Canopy Height Model data(CHM)

A bounded ability estimation for computerized adaptive testing 23

学校读者我要写书评

暂无评论

A bounded ability estimation for computerized adaptive testi...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yan Zhuang Qi Liu GuanHao Zhao Zhenya Huang Weizhe Huang Zachary A. Pardos Enhong Chen Jinze Wu Xin Li Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence University of California Berkeley State Key Laboratory of Cognitive Intelligence and iFLYTEK Co. Ltd

Computerized adaptive testing (CAT), as a tool that can efficiently measure student's ability, has been widely used in various standardized tests (e.g., GMAT and GRE). The adaptivity of CAT refers to the selection of the most informative questions for each student, reducing test length. Existing CAT methods do not explicitly target ability estimation accuracy since there is no student's true ability as ground truth; therefore, these methods cannot be guaranteed to make the estimate converge to the true with such limited responses. In this paper, we analyze the statistical properties of estimation and find a theoretical approximation of the true ability: the ability estimated by full responses to question bank. Based on this, a Bounded Ability Estimation framework for CAT (BECAT) is proposed in a data-summary manner, which selects a question subset that closely matches the gradient of the full responses. Thus, we develop an expected gradient difference approximation to design a simple greedy selection algorithm, and show the rigorous theoretical and error upper-bound guarantees of its ability estimate. Experiments on both real-world and synthetic datasets, show that it can reach the same estimation accuracy using 15% less questions on average, significantly reducing test length.

关键词：