Zobrazeno 1 - 10
of 124
pro vyhledávání: '"CUSANO, CLAUDIO"'
We propose a new method for exemplar-free class incremental training of ViTs. The main challenge of exemplar-free continual learning is maintaining plasticity of the learner without causing catastrophic forgetting of previously learned tasks. This is
Externí odkaz:
http://arxiv.org/abs/2211.12292
Autor:
Cotogni, Marco, Cusano, Claudio
Nowadays, image-to-image translation methods, are the state of the art for the enhancement of natural images. Even if they usually show high performance in terms of accuracy, they often suffer from several limitations such as the generation of artifa
Externí odkaz:
http://arxiv.org/abs/2207.07092
Autor:
Cotogni, Marco, Cusano, Claudio
Publikováno v:
Neurocomputing 2022
In this paper we present a framework for the design and implementation of offset equivariant networks, that is, neural networks that preserve in their output uniform increments in the input. In a suitable color space this kind of networks achieves eq
Externí odkaz:
http://arxiv.org/abs/2207.00292
Autor:
Cotogni, Marco, Cusano, Claudio
In this paper we present TreEnhance, an automatic method for low-light image enhancement capable of improving the quality of digital images. The method combines tree search theory, and in particular the Monte Carlo Tree Search (MCTS) algorithm, with
Externí odkaz:
http://arxiv.org/abs/2205.12639
Autor:
Cotogni, Marco ⁎, Cusano, Claudio
Publikováno v:
In Pattern Recognition Letters July 2024 183:172-178
The recognition of color texture under varying lighting conditions is still an open issue. Several features have been proposed for this purpose, ranging from traditional statistical descriptors to features extracted with neural networks. Still, it is
Externí odkaz:
http://arxiv.org/abs/1508.01108
In this paper we present a method for the estimation of the color of the illuminant in RAW images. The method includes a Convolutional Neural Network that has been specially designed to produce multiple local estimates. A multiple illuminant detector
Externí odkaz:
http://arxiv.org/abs/1508.00998
In this paper we propose a strategy for semi-supervised image classification that leverages unsupervised representation learning and co-training. The strategy, that is called CURL from Co-trained Unsupervised Representation Learning, iteratively buil
Externí odkaz:
http://arxiv.org/abs/1505.08098
In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination. Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most previous meth
Externí odkaz:
http://arxiv.org/abs/1504.04548