Related papers: Augmented Weak Distance for Fast and Accurate Boun…
Weak-value amplification (WVA) is a metrological protocol that effectively amplifies ultra-small physical effects, making it highly applicable in the fields of quantum sensing and metrology. However, the amplification effect is achieved…
Weakly supervised video anomaly detection (WS-VAD) is tasked with pinpointing temporal intervals containing anomalous events within untrimmed videos, utilizing only video-level annotations. However, a significant challenge arises due to the…
Assessing the proper difficulty levels of reading materials or texts in general is the first step towards effective comprehension and learning. In this study, we improve the conventional methodology of automatic readability assessment by…
In this paper, we propose WaterMark Detection (WMD), the first invisible watermark detection method under a black-box and annotation-free setting. WMD is capable of detecting arbitrary watermarks within a given reference dataset using a…
Supporting e-Science in the EGI e-Infrastructure requires extensive and reliable software, for advanced computing use, deployed across over approximately 300 European and worldwide data centers. The Unified Middleware Distribution (UMD) and…
We introduce SAW, a tool for safety analysis of weakly-hard systems, in which traditional hard timing constraints are relaxed to allow bounded deadline misses for improving design flexibility and runtime resiliency. Safety verification is a…
Anomaly Detection (AD) and Anomaly Localization (AL) are crucial in fields that demand high reliability, such as medical imaging and industrial monitoring. However, current AD and AL approaches are often susceptible to adversarial attacks…
On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy distillation and standard reinforcement learning. However, we find that its standard advantage weighted…
This study addresses the critical challenge of error accumulation in spatio-temporal auto-regressive (AR) predictions within scientific machine learning models by exploring temporal integration schemes and adaptive multi-step rollout…
Video Anomaly Detection (VAD) can play a key role in spotting unusual activities in video footage. VAD is difficult to use in real-world settings due to the dynamic nature of human actions, environmental variations, and domain shifts.…
Asynchronous stochastic gradient descent (ASGD) is a popular parallel optimization algorithm in machine learning. Most theoretical analysis on ASGD take a discrete view and prove upper bounds for their convergence rates. However, the…
Neural networks offer a computationally efficient approximation of model predictive control, but they lack guarantees on the resulting controlled system's properties. Formal certification of neural networks is crucial for ensuring safety,…
With the advent of Advanced Driver Assistance Systems (ADAS), there is an increasing need to evaluate driver behavior while using such technology. In this unique study, a forward collision warning (FCW) system using connected vehicle…
Visual Anomaly Detection (VAD) is a critical task in computer vision with numerous real-world applications. However, deploying these models on edge devices presents significant challenges, such as constrained computational and memory…
The objective of this paper is to design an efficient and convergent alternating direction method of multipliers (ADMM) for finding a solution of medium accuracy to conic programming problems whose constraints consist of linear equalities,…
Artificial Neural networks (ANNs) are powerful computing systems employed for various applications due to their versatility to generalize and to respond to unexpected inputs/patterns. However, implementations of ANNs for safety-critical…
Adversarial attacks play a pivotal role in testing and improving the reliability of deep learning (DL) systems. Existing literature has demonstrated that subtle perturbations to the input can elicit erroneous outcomes, thereby substantially…
Mirror descent (MD) is a powerful first-order optimization technique that subsumes several optimization algorithms including gradient descent (GD). In this work, we develop a semi-definite programming (SDP) framework to analyze the…
We propose an efficient ADMM method with guarantees for high-dimensional problems. We provide explicit bounds for the sparse optimization problem and the noisy matrix decomposition problem. For sparse optimization, we establish that the…
Porting a scientific data analysis workflow (DAW) to a cluster infrastructure, a new software stack, or even only a new dataset with some notably different properties is often challenging. Despite the structured definition of the steps…