Now showing items 1-7 of 7

    • A confusion matrix for evaluating feature attribution methods 

      Arias Duart, Anna; Mariotti, Ettore; Garcia Gasulla, Dario; Alonso Moral, Jose Maria (Institute of Electrical and Electronics Engineers (IEEE), 2023)
      Conference lecture
      Open Access
      The increasing use of deep learning models in critical areas of computer vision and the consequent need for insights into model behaviour have led to the development of numerous feature attribution methods. However, these ...
    • Assessing biases through mosaic attributions 

      Arias Duart, Anna (Universitat Politècnica de Catalunya, 2023-12-11)
      Doctoral thesis
      Open Access
      (English) Machine learning and, more specifically, deep learning applications have grown in number in recent years. These intelligent systems have shown remarkable performance across various domains, including sensitive ...
    • Assessing biases through visual contexts 

      Arias Duart, Anna; Giménez Ábalos, Víctor; Cortés García, Claudio Ulises; Garcia Gasulla, Dario (2023-07)
      Article
      Open Access
      Bias detection in the computer vision field is a necessary task, to achieve fair models. These biases are usually due to undesirable correlations present in the data and learned by the model. Although explainability can ...
    • Focus and bias: will it blend? 

      Arias Duart, Anna; Parés Pont, Ferran; Giménez Ábalos, Víctor; Garcia Gasulla, Dario (IOS Press, 2022)
      Conference report
      Open Access
      One 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 

      Arias Duart, Anna; Parés Pont, Ferran; Garcia Gasulla, Dario; Giménez Ábalos, Víctor (Institute of Electrical and Electronics Engineers (IEEE), 2022)
      Conference report
      Open Access
      AI 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 ...
    • Focus! rating XAI methods and finding biases 

      Arias Duart, Anna; Parés, Ferran; Garcia-Gasulla, Dario (Barcelona Supercomputing Center, 2022-05)
      Conference report
      Open Access
      Explainability 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 ...
    • The MAMe dataset: On the relevance of high resolution and variable shape image properties 

      Parés Pont, Ferran; Arias Duart, Anna; Garcia Gasulla, Dario; Campo Francés, Gema; Viladrich Iglesias, Nina; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José (Springer, 2022-08)
      Article
      Open Access
      The 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 ...