Zobrazeno 1 - 10
of 4 280
pro vyhledávání: '"Luzi P"'
Publikováno v:
Diglosia, Vol 7, Iss 2 (2024)
The purpose of this research is to analyze the role of the environment in the learning and preservation of the Serawai language, also known as ecolinguistics. A qualitative approach with a descriptive method is used in this research to describe the r
Externí odkaz:
https://doaj.org/article/8ce4ccf100464751849c5cbeeb71dd12
Image classification models, including convolutional neural networks (CNNs), perform well on a variety of classification tasks but struggle under conditions of partial occlusion, i.e., conditions in which objects are partially covered from the view o
Externí odkaz:
http://arxiv.org/abs/2409.10775
Generative models unfairly penalize data belonging to minority classes, suffer from model autophagy disorder (MADness), and learn biased estimates of the underlying distribution parameters. Our theoretical and empirical results show that training gen
Externí odkaz:
http://arxiv.org/abs/2405.13977
The rapid advancement of Generative Adversarial Networks (GANs) necessitates the need to robustly evaluate these models. Among the established evaluation criteria, the Fr\'{e}chetInception Distance (FID) has been widely adopted due to its conceptual
Externí odkaz:
http://arxiv.org/abs/2310.20636
Autor:
Alemohammad, Sina, Casco-Rodriguez, Josue, Luzi, Lorenzo, Humayun, Ahmed Imtiaz, Babaei, Hossein, LeJeune, Daniel, Siahkoohi, Ali, Baraniuk, Richard G.
Seismic advances in generative AI algorithms for imagery, text, and other data types has led to the temptation to use synthetic data to train next-generation models. Repeating this process creates an autophagous (self-consuming) loop whose properties
Externí odkaz:
http://arxiv.org/abs/2307.01850
Autor:
Ren, Simiao, Luzi, Francesco, Lahrichi, Saad, Kassaw, Kaleb, Collins, Leslie M., Bradbury, Kyle, Malof, Jordan M.
Recently, the first foundation model developed specifically for image segmentation tasks was developed, termed the "Segment Anything Model" (SAM). SAM can segment objects in input imagery based on cheap input prompts, such as one (or more) points, a
Externí odkaz:
http://arxiv.org/abs/2304.13000
Recent object detection models for infrared (IR) imagery are based upon deep neural networks (DNNs) and require large amounts of labeled training imagery. However, publicly-available datasets that can be used for such training are limited in their si
Externí odkaz:
http://arxiv.org/abs/2212.12824
We study the generalization behavior of transfer learning of deep neural networks (DNNs). We adopt the overparameterization perspective -- featuring interpolation of the training data (i.e., approximately zero train error) and the double descent phen
Externí odkaz:
http://arxiv.org/abs/2211.11074
Autor:
Luzi, Lorenzo, LeJeune, Daniel, Siahkoohi, Ali, Alemohammad, Sina, Saragadam, Vishwanath, Babaei, Hossein, Liu, Naiming, Wang, Zichao, Baraniuk, Richard G.
We study the interpolation capabilities of implicit neural representations (INRs) of images. In principle, INRs promise a number of advantages, such as continuous derivatives and arbitrary sampling, being freed from the restrictions of a raster grid.
Externí odkaz:
http://arxiv.org/abs/2211.00219
There is evidence that transformers offer state-of-the-art recognition performance on tasks involving overhead imagery (e.g., satellite imagery). However, it is difficult to make unbiased empirical comparisons between competing deep learning models,
Externí odkaz:
http://arxiv.org/abs/2210.12599