Browsing by Author "Parés Pont, Ferran"
Now showing items 1-11 of 11
-
Automated image analysis for single-atom detection in catalytic materials by transmission electron microscopy
(2022-03-25)
Article
Open AccessSingle-atom catalytic sites may have existed in all supported transition metal catalysts since their first application. Yet, interest in the design of single-atom heterogeneous catalysts (SACs) only really grew when advances ... -
Building graph representations of deep vector embeddings
(Association for Computational Linguistics, 2017)
Conference lecture
Open AccessPatterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes. Typically, deep network representations are implemented within vector ... -
Flota de robots móviles para el reconocimiento automático del entorno
(Universitat Politècnica de Catalunya, 2014-06-11)
Bachelor thesis
Open AccessAquest projecte té com objectiu el disseny i muntatge d’un sistema compost per tres robots mòbils i una unitat central. Aquest sistema pretén servir com a plataforma de desenvolupament per a tècniques SLAM. Cada robot ... -
Focus and bias: will it blend?
(IOS Press, 2022)
Conference report
Open AccessOne direct application of explainable AI feature attribution methods is to be used for detecting unwanted biases. To do so, domain experts typically have to review explained inputs, checking for the presence of unwanted ... -
Focus! Rating XAI methods and finding biases
(Institute of Electrical and Electronics Engineers (IEEE), 2022)
Conference report
Open AccessAI explainability improves the transparency and trustworthiness of models. However, in the domain of images, where deep learning has succeeded the most, explainability is still poorly assessed. In the field of image ... -
Full-network embedding in a multimodal embedding pipeline
(Association for Computational Linguistics, 2017)
Conference lecture
Open AccessThe current state-of-the-art for image annotation and image retrieval tasks is obtained through deep neural networks, which combine an image representation and a text representation into a shared embedding space. In this ... -
Image Aesthetic Learning with Deep Convolutional Neural Networks
(Universitat Politècnica de Catalunya, 2016-04-14)
Master thesis
Restricted access - confidentiality agreement -
MetH: A family of high-resolution and variable-shape image challenges
(2019-11-20)
Research report
Open AccessHigh-resolution and variable-shape images have not yet been properly addressed by the AI community. The approach of down-sampling data often used with convolutional neural networks is sub-optimal for many tasks, and has ... -
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 ... -
Size & shape matters: The need of HPC benchmarks of high resolution image training for deep learning
(2021-03)
Article
Open AccessOne of the purposes of HPC benchmarks is to identify limitations and bottlenecks in hardware. This functionality is particularly influential when assessing performance on emerging tasks, the nature and requirements of which ... -
The MAMe dataset: On the relevance of high resolution and variable shape image properties
(Springer, 2022-08)
Article
Open AccessThe mostcommon approach in image classification tasks is to resize all images in the dataset to a unique shape, while reducing their resolution to a size that makes experimentation at scale easier. This practice has benefits ...
