Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Malossi, Cristiano"'
Instance segmentation datasets play a crucial role in training accurate and robust computer vision models. However, obtaining accurate mask annotations to produce high-quality segmentation datasets is a costly and labor-intensive process. In this wor
Externí odkaz:
http://arxiv.org/abs/2402.16421
Autor:
Kimmich, Maximilian, Bartezzaghi, Andrea, Bogojeska, Jasmina, Malossi, Cristiano, Vu, Ngoc Thang
Neural approaches have become very popular in Question Answering (QA), however, they require a large amount of annotated data. In this work, we propose a novel approach that combines data augmentation via question-answer generation with Active Learni
Externí odkaz:
http://arxiv.org/abs/2211.14880
Autor:
Frick, Thomas, Antognini, Diego, Rigotti, Mattia, Giurgiu, Ioana, Grewe, Benjamin, Malossi, Cristiano
Aging civil infrastructures are closely monitored by engineers for damage and critical defects. As the manual inspection of such large structures is costly and time-consuming, we are working towards fully automating the visual inspections to support
Externí odkaz:
http://arxiv.org/abs/2210.10586
Labeling images for visual segmentation is a time-consuming task which can be costly, particularly in application domains where labels have to be provided by specialized expert annotators, such as civil engineering. In this paper, we propose to use a
Externí odkaz:
http://arxiv.org/abs/2209.11159
Artificial Intelligence (AI) development is inherently iterative and experimental. Over the course of normal development, especially with the advent of automated AI, hundreds or thousands of experiments are generated and are often lost or never exami
Externí odkaz:
http://arxiv.org/abs/2202.10979
In this work, we leverage ensemble learning as a tool for the creation of faster, smaller, and more accurate deep learning models. We demonstrate that we can jointly optimize for accuracy, inference time, and the number of parameters by combining DNN
Externí odkaz:
http://arxiv.org/abs/2009.08698
This paper reduces the cost of DNNs training by decreasing the amount of data movement across heterogeneous architectures composed of several GPUs and multicore CPU devices. In particular, this paper proposes an algorithm to dynamically adapt the dat
Externí odkaz:
http://arxiv.org/abs/2004.02297
Deep neural networks achieve outstanding results in challenging image classification tasks. However, the design of network topologies is a complex task and the research community makes a constant effort in discovering top-accuracy topologies, either
Externí odkaz:
http://arxiv.org/abs/1909.10818
Autor:
Scheidegger, Florian, Istrate, Roxana, Mariani, Giovanni, Benini, Luca, Bekas, Costas, Malossi, Cristiano
In the deep-learning community new algorithms are published at an incredible pace. Therefore, solving an image classification problem for new datasets becomes a challenging task, as it requires to re-evaluate published algorithms and their different
Externí odkaz:
http://arxiv.org/abs/1803.09588
Image classification datasets are often imbalanced, characteristic that negatively affects the accuracy of deep-learning classifiers. In this work we propose balancing GAN (BAGAN) as an augmentation tool to restore balance in imbalanced datasets. Thi
Externí odkaz:
http://arxiv.org/abs/1803.09655