Zobrazeno 1 - 10
of 1 204
pro vyhledávání: '"Cuzzolin A"'
This paper explores the utility of diffusion-based models for anomaly detection, focusing on their efficacy in identifying deviations in both compact and high-resolution datasets. Diffusion-based architectures, including Denoising Diffusion Probabili
Externí odkaz:
http://arxiv.org/abs/2412.07539
The aim of this paper is to formalise the task of continual semi-supervised anomaly detection (CSAD), with the aim of highlighting the importance of such a problem formulation which assumes as close to real-world conditions as possible. After an over
Externí odkaz:
http://arxiv.org/abs/2412.00860
Autor:
Khan, Salman, Teeti, Izzeddin, Alitappeh, Reza Javanmard, Stoian, Mihaela C., Giunchiglia, Eleonora, Singh, Gurkirt, Bradley, Andrew, Cuzzolin, Fabio
Autonomous Vehicle (AV) perception systems require more than simply seeing, via e.g., object detection or scene segmentation. They need a holistic understanding of what is happening within the scene for safe interaction with other road users. Few dat
Externí odkaz:
http://arxiv.org/abs/2411.01683
This paper presents an innovative approach, called credal wrapper, to formulating a credal set representation of model averaging for Bayesian neural networks (BNNs) and deep ensembles, capable of improving uncertainty estimation in classification tas
Externí odkaz:
http://arxiv.org/abs/2405.15047
The complexity of scene parsing grows with the number of object and scene classes, which is higher in unrestricted open scenes. The biggest challenge is to model the spatial relation between scene elements while succeeding in identifying objects at s
Externí odkaz:
http://arxiv.org/abs/2402.19250
Autor:
Cuzzolin, Fabio
The purpose of this paper is to look into how central notions in statistical learning theory, such as realisability, generalise under the assumption that train and test distribution are issued from the same credal set, i.e., a convex set of probabili
Externí odkaz:
http://arxiv.org/abs/2402.14759
Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learned from a (single) training set, assumed to issue from an unknown probability distribution. In actual deployment, however, the
Externí odkaz:
http://arxiv.org/abs/2402.00957
Autor:
Wang, Kaizheng, Shariatmadar, Keivan, Manchingal, Shireen Kudukkil, Cuzzolin, Fabio, Moens, David, Hallez, Hans
Uncertainty estimation is increasingly attractive for improving the reliability of neural networks. In this work, we present novel credal-set interval neural networks (CreINNs) designed for classification tasks. CreINNs preserve the traditional inter
Externí odkaz:
http://arxiv.org/abs/2401.05043
Interpretation and understanding of video presents a challenging computer vision task in numerous fields - e.g. autonomous driving and sports analytics. Existing approaches to interpreting the actions taking place within a video clip are based upon T
Externí odkaz:
http://arxiv.org/abs/2310.17493
Autor:
Teeti, Izzeddin, Bhargav, Rongali Sai, Singh, Vivek, Bradley, Andrew, Banerjee, Biplab, Cuzzolin, Fabio
The emerging field of action prediction plays a vital role in various computer vision applications such as autonomous driving, activity analysis and human-computer interaction. Despite significant advancements, accurately predicting future actions re
Externí odkaz:
http://arxiv.org/abs/2308.04589