Filters








3 Hits in 2.7 sec

AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation [article]

Masataka Yamaguchi, Yuma Koizumi, Noboru Harada
2019 arXiv   pre-print
We also propose a method of applying AdaFlow to the unpaired cross-domain translation problem, in which one has to train a cross-domain translation model with only unpaired samples.  ...  To address this difficulty, we propose AdaFlow, a new DNN-based density estimator that can be easily adapted to the change of the distribution.  ...  APPLICATION TO UNPAIRED CROSS-DOMAIN TRANSLATION Though AdaFlow was originally designed for conducting density estimation on multiple domains, we demonstrate that it can be also used for the unpaired cross-domain  ... 
arXiv:1812.05796v2 fatcat:aj2undvyfbboxdmjksuyynlegy

Comparison of Anomaly Detectors: Context Matters [article]

Vít Škvára, Jan Franců, Matěj Zorek, Tomáš Pevný, Václav Šmídl
2021 arXiv   pre-print
The objective of this comparison is twofold: to compare anomaly detection methods of various paradigms with focus on deep generative models, and identification of sources of variability that can yield  ...  We identified the main sources of variability to be experimental conditions: i) the type data set (tabular or image) and the nature of anomalies (statistical or semantic), and ii) strategy of selection  ...  [93] Masataka Yamaguchi, Yuma Koizumi, and Noboru Harada. Adaflow: Domain-adaptive density estimator with application to anomaly detection and unpaired cross-domain translation.  ... 
arXiv:2012.06260v3 fatcat:min2zullxrbupf36o6uoeauwhi

Robust Audio Anomaly Detection

Wo Jae Lee, Karim Helwani, Arvindh Krishnaswamy, Srikanth Tenneti
2022
The presented approach doesn't assume the presence of labeled anomalies in the training dataset and uses a novel deep neural network architecture to learn the temporal dynamics of the multivariate time  ...  We demonstrate the effectiveness of our approach in anomaly detection by comparing against several state-of-the-art models.  ...  Adaflow: Domain-adaptive density estimator with application to anomaly detection and unpaired cross-domain translation. pp. 3647-3651. IEEE, 2019.  ... 
doi:10.48550/arxiv.2202.01784 fatcat:bkkdljcq65evnkgvldy25hgdte