This article addresses the problem of the non-circulation of information in each stage of architectural design. This paper explores the architectural design process based on the BIM platform and puts forward the struc...
详细信息
Materials synthesis is vital for innovations such as energy storage, catalysis, electronics, and biomedical devices. Yet, the process relies heavily on empirical, trial-and-error methods guided by expert intuition. Ou...
详细信息
Performance fairness has always been a key issue in federated learning (FL), however, the pursuit of performance consistency can lead to a trade-off where the accuracy of well-performing clients is compromised to enha...
详细信息
Supporting vehicular emergency applications requires fast access to infrastructure so vehicles can call for help. Because of their environment's poor wireless qualities, vehicle-infrastructure communication paths ...
详细信息
作者：
Shahin, NadaIsmail, LeilaLab
Department of Computer Science and Software Engineering College of Information Technology UAE University Al-Ain United Arab Emirates Lab
Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates Emirates Center for Mobility Research UAE University
Al-Ain United Arab Emirates
Machine Translation has played a critical role in reducing language barriers, but its adaptation for Sign Language Machine Translation (SLMT) has been less explored. Existing works on SLMT mostly use the Transformer n...
详细信息
Deep supervised learning has demonstrated strong capabilities; however, such progress relies on massive and expensive data annotation. Active Learning (AL) has been introduced to selectively annotate samples, thus red...
Deep supervised learning has demonstrated strong capabilities; however, such progress relies on massive and expensive data annotation. Active Learning (AL) has been introduced to selectively annotate samples, thus reducing the human labeling effort. Previous AL research has focused on employing recently trained models to design sampling strategies, based on uncertainty or representativeness. Drawing inspiration from the issue of model forgetting, we propose a novel AL framework called Temporal Inconsistency-Based Active Learning (TIR-AL). In this framework, multiple snapshots of the models across consecutive cycles are jointly utilized to select samples with higher temporal inconsistency, by computing the proposed self-weighted nuclear norm metric. Furthermore, we introduce a consistency regularization term to mitigate the issue of forgetting. Together, these components make full use of the potential of data and facilitate effective interaction within the AL loop. To demonstrate the efficacy of TIR-AL, we conducted a set of experiments illustrating how our approach outperforms state-of-the-art methods without incurring any additional training costs.
Background: The COVID-19 outbreak interrupted regular activities for over a year in many countries and resulted in a radical change in ways of working for software development companies, i.e., most software developmen...
详细信息
We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both off-line and on-line settings. Our analysis highlights ...
作者：
Xinsong MaXin ZouWeiwei LiuSchool of Computer Science
National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China
Out-of-distribution (OOD) detection task plays the key role in reliable and safety-critical applications. Existing researches mainly devote to designing or training the powerful score function but overlook investigati...
Out-of-distribution (OOD) detection task plays the key role in reliable and safety-critical applications. Existing researches mainly devote to designing or training the powerful score function but overlook investigating the decision rule based on the proposed score function. Different from previous work, this paper aims to design a decision rule with rigorous theoretical guarantee and well empirical performance. Specifically, we provide a new insight for the OOD detection task from a hypothesis testing perspective and propose a novel generalized Benjamini Hochberg (g-BH) procedure with empirical p-values to solve the testing problem. Theoretically, the g-BH procedure controls false discovery rate (FDR) at pre-specified level. Furthermore, we derive an upper bound of the expectation of false positive rate (FPR) for the g-BH procedure based on the tailed generalized Gaussian distribution family, indicating that the FPR of g-BH procedure converges to zero in probability. Finally, the extensive experimental results verify the superiority of g-BH procedure over the traditional threshold-based decision rule on several OOD detection benchmarks.
With the rising prevalence of smart homes, there's an increasing demand for comprehensive automation solutions to mitigate fire risks, especially when homeowners are absent or in homes with elderly residents. This...
详细信息
暂无评论