Results 11 to 20 of about 178,877 (269)
Unsupervised Part Discovery by Unsupervised Disentanglement [PDF]
, 2021 GCPR 2020 (Oral)
Sandro Braun +2 more
openaire +2 more sources
CoRR, 2021 This paper studies "unsupervised finetuning", the symmetrical problem of the well-known "supervised finetuning". Given a pretrained model and small-scale unlabeled target data, unsupervised finetuning is to adapt the representation pretrained from the source domain to the target domain so that better transfer performance can be obtained.
Suichan Li +7 more
openaire +2 more sources
American Journal of Orthodontics and Dentofacial Orthopedics, 2023 This work was supported by the Flemish Government under the “Onderzoeksprogramma Artifici€ele Intelligentie (AI) Vlaanderen ...
Dirk Valkenborg +3 more
openaire +3 more sources
Evaluating Unsupervised Denoising Requires Unsupervised Metrics
CoRR, 2022 Unsupervised denoising is a crucial challenge in real-world imaging applications. Unsupervised deep-learning methods have demonstrated impressive performance on benchmarks based on synthetic noise. However, no metrics are available to evaluate these methods in an unsupervised fashion. This is highly problematic for the many practical applications where
Adria Marcos-Morales +7 more
openaire +3 more sources
, 2012 The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-33885-4_41 Proceedings of Information Fusion in Computer Vision for Concept Recognition at the ECCV 2012 In this paper we present a new model of semantic features that, unlike previously presented methods, does not rely on the presence of a labeled training data base,
Claudio Cusano +2 more
openaire +2 more sources
Unsupervised discovery of morphemes [PDF]
Proceedings of the ACL-02 workshop on Morphological and phonological learning -, 2002 We present two methods for unsupervised segmentation of words into morpheme-like units. The model utilized is especially suited for languages with a rich morphology, such as Finnish. The first method is based on the Minimum Description Length (MDL) principle and works online. In the second method, Maximum Likelihood (ML) optimization is used.
Mathias Creutz, Krista Lagus
openaire +2 more sources
Video Object Segmentation by Latent Outcome Regression
IEEE Access, 2020 This paper presents a novel algorithm for unsupervised video object segmentation (UVOS) in unconstrained scenarios. Although a large variety of methods have been proposed in the literature, segmenting generic objects is still challenging because ...
Lin Zhang, Yao Lu
doaj +1 more source
Unsupervised Learning of Morphology [PDF]
Computational Linguistics, 2011 This article surveys work on Unsupervised Learning of Morphology. We define Unsupervised Learning of Morphology as the problem of inducing a description (of some kind, even if only morpheme-segmentation) of how orthographic words are built up given only raw text data of a language.
Hammarström, H. ; https://orcid.org/0000-0003-0120-6396 +1 more
openaire +6 more sources
Unsupervised learning and generalization [PDF]
Proceedings of International Conference on Neural Networks (ICNN'96), 2002 The concept of generalization is defined for a general class of unsupervised learning machines. The generalization error is a straightforward extension of the corresponding concept for supervised learning, and may be estimated empirically using a test set or by statistical means-in close analogy with supervised learning.
Lars Kai Hansen, Jan Larsen
openaire +2 more sources
Video Scene Segmentation of TV Series Using Multimodal Neural Features
Series. International journal of tv serial narratives, 2019 Scene segmentation of a video, a book or TV series allows to organize them into Logical Story Units and is an essential step for representing, extracting and understanding their narrative structures.
Aman Berhe +2 more
doaj +1 more source