Browsing by Author "Garcia-Gasulla, Dario"
Now showing items 1-5 of 5
-
An out-of-the-box full-network embedding for convolutional neural networks
(Institute of Electrical and Electronics Engineers (IEEE), 2018)
Conference report
Open AccessFeatures extracted through transfer learning can be used to exploit deep learning representations in contexts where there are very few training samples, where there are limited computational resources, or when the tuning ... -
Focus! rating XAI methods and finding biases
(Barcelona Supercomputing Center, 2022-05)
Conference report
Open AccessExplainability has become a major topic of research in Artificial Intelligence (AI), aimed at increasing trust in models such as Deep Learning (DL) networks. However, trustworthy models cannot be achieved with explainable ... -
On the behavior of convolutional nets for feature extraction
(2018-03)
Article
Open AccessDeep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive ... -
Studying the impact of the Full-Network embedding on multimodal pipelines
(IOS Press, 2019-09-26)
Article
Open AccessThe current state of the art for image annotation and image retrieval tasks is obtained through deep neural network multimodal pipelines, which combine an image representation and a text representation into a shared embedding ... -
Training CNNs using high-resolution images of variable shape
(Barcelona Supercomputing Center, 2019-05-07)
Conference report
Open Access
