2025
Authors
Montenegro, H; Cardoso, MJ; Cardoso, JS;
Publication
CoRR
Abstract
2025
Authors
Vieira, AB; Valente, M; Montezuma, D; Albuquerque, T; Ribeiro, L; Oliveira, D; Monteiro, JC; Gonçalves, S; Pinto, IM; Cardoso, JS; Oliveira, AL;
Publication
CoRR
Abstract
2025
Authors
Caetano, F; Carvalho, P; Mastralexi, C; Cardoso, S;
Publication
IEEE Access
Abstract
Anomaly Detection has been a significant field in Machine Learning since it began gaining traction. In the context of Computer Vision, the increased interest is notorious as it enables the development of video processing models for different tasks without the need for a cumbersome effort with the annotation of possible events, that may be under represented. From the predominant strategies, weakly and semi-supervised, the former has demonstrated potential to achieve a higher score in its analysis, adding to its flexibility. This work shows that using temporal ranking constraints for Multiple Instance Learning can increase the performance of these models, allowing the focus on the most informative instances. Moreover, the results suggest that altering the ranking process to include information about adjacent instances generates best-performing models. © 2013 IEEE.
2025
Authors
Pinto, JR; Cardoso, S;
Publication
Encyclopedia of Cryptography, Security and Privacy, Third Edition
Abstract
[No abstract available]
2025
Authors
Coelho, B; Cardoso, S;
Publication
Neurocomputing
Abstract
In order to facilitate the adoption of deep learning in areas where decisions are of critical importance, understanding the model's internal workings is paramount. Nevertheless, since most models are considered black boxes, this task is usually not trivial, especially when the user does not have access to the network's intermediate outputs. In this paper, we propose IBISA, a model-agnostic attribution method that reaches state-of-the-art performance by optimizing sampling masks using the Information Bottleneck Principle. Our method improves on the previously known RISE and IBA techniques by placing the bottleneck right after the image input without complex formulations to estimate the mutual information. The method also requires only twenty forward passes and ten backward passes through the network, which is significantly faster than RISE, which needs at least 4000 forward passes. We evaluated IBISA using a VGG-16 and a ResNET-50 model, showing that our method produces explanations comparable or superior to IBA, RISE, and Grad-CAM but much more efficiently. © 2025 The Authors
2025
Authors
Nunes, JD; Montezuma, D; Oliveira, D; Pereira, T; Zlobec, I; Pinto, IM; Cardoso, JS;
Publication
Sensors
Abstract
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.