Zobrazeno 1 - 10
of 353
pro vyhledávání: '"Kilickaya A"'
Condition monitoring of induction machines is crucial to prevent costly interruptions and equipment failure. Mechanical faults such as misalignment and rotor issues are among the most common problems encountered in industrial environments. To effecti
Externí odkaz:
http://arxiv.org/abs/2412.05901
Hyperspectral Imaging (HSI) plays an increasingly critical role in precise vision tasks within remote sensing, capturing a wide spectrum of visual data. Transformer architectures have significantly enhanced HSI task performance, while advancements in
Externí odkaz:
http://arxiv.org/abs/2407.16269
Autor:
Kilickaya, Mert, Vanschoren, Joaquin
This position paper outlines the potential of AutoML for incremental (continual) learning to encourage more research in this direction. Incremental learning involves incorporating new data from a stream of tasks and distributions to learn enhanced de
Externí odkaz:
http://arxiv.org/abs/2311.11963
Hyperspectral image classification is gaining popularity for high-precision vision tasks in remote sensing, thanks to their ability to capture visual information available in a wide continuum of spectra. Researchers have been working on automating Hy
Externí odkaz:
http://arxiv.org/abs/2309.01561
Publikováno v:
2023 Photonics & Electromagnetics Research Symposium (PIERS)
Hyperspectral image (HSI) classification is an important task in many applications, such as environmental monitoring, medical imaging, and land use/land cover (LULC) classification. Due to the significant amount of spectral information from recent HS
Externí odkaz:
http://arxiv.org/abs/2304.09730
Class-Incremental Learning aims to update a deep classifier to learn new categories while maintaining or improving its accuracy on previously observed classes. Common methods to prevent forgetting previously learned classes include regularizing the n
Externí odkaz:
http://arxiv.org/abs/2303.13113
The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence. Such an approach is non-incremental, as it assumes access to all images of all categories at once. However, for many ap
Externí odkaz:
http://arxiv.org/abs/2302.00353
Autor:
Kilickaya, Mert, Vanschoren, Joaquin
In this paper, we learn to classify visual object instances, incrementally and via self-supervision (self-incremental). Our learner observes a single instance at a time, which is then discarded from the dataset. Incremental instance learning is chall
Externí odkaz:
http://arxiv.org/abs/2301.11417
Autor:
Merve Ider, Ceylan Ceylan, Amir Naseri, Onur Ceylan, Murat Kaan Durgut, Mahmut Ok, Suleyman Serhat Iyigun, Busra Burcu Erol, Hatice Betul Sahin, Merve Cansu Kilickaya
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-11 (2024)
Abstract The present study aimed to investigate endothelial glycocalyx (eGCx) damage in cats with feline hemotropic mycoplasmosis caused by Mycoplasma haemofelis using selected biomarkers and to determine the diagnostic and prognostic significance of
Externí odkaz:
https://doaj.org/article/fe0d4ae0c6d6438780fb453456f1f316
In this paper, our goal is to adapt a pre-trained convolutional neural network to domain shifts at test time. We do so continually with the incoming stream of test batches, without labels. The existing literature mostly operates on artificial shifts
Externí odkaz:
http://arxiv.org/abs/2208.08767