Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Sobre

Sobre

Jaime S. Cardoso, licenciado em Engenharia e Eletrotécnica e de Computadores em 1999, Mestre em Engenharia Matemática em 2005 e doutorado em Visão Computacional em 2006, todos pela Universidade do Porto. Professor Associado com agregação na Faculdade de Engenharia da Universidade do Porto (FEUP) e Investigador Sénior em 'Information Processing and Pattern Recognition' no Centro de Telecomunicações e Multimédia do INESC TEC.

A sua investigação assenta em três grandes domínios: visão computacional, "machine learning" e sistemas de suporte à decisão. A investigação em processamento de imagem e vídeo tem abordado a área de biometria, imagem médica e "video tracking" para aplicações de vigilância e desportos. O trabalho em "machine learning" foca-se na adaptação de sistemas de aprendizagem às condições desafiantes de informação visual. A ênfase dos sistemas de suporte à decisão tem sido dirigida a aplicações médicas, sempre ancoradas com a análise automática de informação visual.

É co-autor de mais de 150 artigos, dos quais mais de 50 em jornais internacionais, com mais de 6500 citações (google scholar). Foi investigador principal em 6 projectos de I&D e participou em 14 projectos de I&D, incluindo 5 projectos europeus e um contrato directo com a BBC do Reino Unido.

Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Jaime Cardoso
  • Cargo

    Investigador Coordenador
  • Desde

    15 setembro 1998
019
Publicações

2024

Classification of Pulmonary Nodules in 2-[<SUP>18</SUP>F]FDG PET/CT Images with a 3D Convolutional Neural Network

Autores
Alves, VM; Cardoso, JD; Gama, J;

Publicação
NUCLEAR MEDICINE AND MOLECULAR IMAGING

Abstract
Purpose 2-[F-18]FDG PET/CT plays an important role in the management of pulmonary nodules. Convolutional neural networks (CNNs) automatically learn features from images and have the potential to improve the discrimination between malignant and benign pulmonary nodules. The purpose of this study was to develop and validate a CNN model for classification of pulmonary nodules from 2-[F-18]FDG PET images.Methods One hundred thirteen participants were retrospectively selected. One nodule per participant. The 2-[F-18]FDG PET images were preprocessed and annotated with the reference standard. The deep learning experiment entailed random data splitting in five sets. A test set was held out for evaluation of the final model. Four-fold cross-validation was performed from the remaining sets for training and evaluating a set of candidate models and for selecting the final model. Models of three types of 3D CNNs architectures were trained from random weight initialization (Stacked 3D CNN, VGG-like and Inception-v2-like models) both in original and augmented datasets. Transfer learning, from ImageNet with ResNet-50, was also used.Results The final model (Stacked 3D CNN model) obtained an area under the ROC curve of 0.8385 (95% CI: 0.6455-1.0000) in the test set. The model had a sensibility of 80.00%, a specificity of 69.23% and an accuracy of 73.91%, in the test set, for an optimised decision threshold that assigns a higher cost to false negatives.Conclusion A 3D CNN model was effective at distinguishing benign from malignant pulmonary nodules in 2-[F-18]FDG PET images.

2024

Active Supervision: Human in the Loop

Autores
Cruz, RPM; Shihavuddin, ASM; Maruf, MH; Cardoso, JS;

Publicação
PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, CIARP 2023, PT I

Abstract
After the learning process, certain types of images may not be modeled correctly because they were not well represented in the training set. These failures can then be compensated for by collecting more images from the real-world and incorporating them into the learning process - an expensive process known as active learning. The proposed twist, called active supervision, uses the model itself to change the existing images in the direction where the boundary is less defined and requests feedback from the user on how the new image should be labeled. Experiments in the context of class imbalance show the technique is able to increase model performance in rare classes. Active human supervision helps provide crucial information to the model during training that the training set lacks.

2024

Explaining Bounding Boxes in Deep Object Detectors Using Post Hoc Methods for Autonomous Driving Systems

Autores
Nogueira, C; Fernandes, L; Fernandes, JND; Cardoso, JS;

Publicação
SENSORS

Abstract
Deep learning has rapidly increased in popularity, leading to the development of perception solutions for autonomous driving. The latter field leverages techniques developed for computer vision in other domains for accomplishing perception tasks such as object detection. However, the black-box nature of deep neural models and the complexity of the autonomous driving context motivates the study of explainability in these models that perform perception tasks. Moreover, this work explores explainable AI techniques for the object detection task in the context of autonomous driving. An extensive and detailed comparison is carried out between gradient-based and perturbation-based methods (e.g., D-RISE). Moreover, several experimental setups are used with different backbone architectures and different datasets to observe the influence of these aspects in the explanations. All the techniques explored consist of saliency methods, making their interpretation and evaluation primarily visual. Nevertheless, numerical assessment methods are also used. Overall, D-RISE and guided backpropagation obtain more localized explanations. However, D-RISE highlights more meaningful regions, providing more human-understandable explanations. To the best of our knowledge, this is the first approach to obtaining explanations focusing on the regression of the bounding box coordinates.

2024

Intrinsic Explainability for End-to-End Object Detection

Autores
Fernandes, L; Fernandes, JND; Calado, M; Pinto, JR; Cerqueira, R; Cardoso, JS;

Publicação
IEEE ACCESS

Abstract
Deep Learning models are automating many daily routine tasks, indicating that in the future, even high-risk tasks will be automated, such as healthcare and automated driving areas. However, due to the complexity of such deep learning models, it is challenging to understand their reasoning. Furthermore, the black box nature of the designed deep learning models may undermine public confidence in critical areas. Current efforts on intrinsically interpretable models focus only on classification tasks, leaving a gap in models for object detection. Therefore, this paper proposes a deep learning model that is intrinsically explainable for the object detection task. The chosen design for such a model is a combination of the well-known Faster-RCNN model with the ProtoPNet model. For the Explainable AI experiments, the chosen performance metric was the similarity score from the ProtoPNet model. Our experiments show that this combination leads to a deep learning model that is able to explain its classifications, with similarity scores, using a visual bag of words, which are called prototypes, that are learned during the training process. Furthermore, the adoption of such an explainable method does not seem to hinder the performance of the proposed model, which achieved a mAP of 69% in the KITTI dataset and a mAP of 66% in the GRAZPEDWRI-DX dataset. Moreover, our explanations have shown a high reliability on the similarity score.

2024

YOLOMM - You Only Look Once for Multi-modal Multi-tasking

Autores
Campos, F; Cerqueira, FG; Cruz, RPM; Cardoso, JS;

Publicação
PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, CIARP 2023, PT I

Abstract
Autonomous driving can reduce the number of road accidents due to human error and result in safer roads. One important part of the system is the perception unit, which provides information about the environment surrounding the car. Currently, most manufacturers are using not only RGB cameras, which are passive sensors that capture light already in the environment but also Lidar. This sensor actively emits laser pulses to a surface or object and measures reflection and time-of-flight. Previous work, YOLOP, already proposed a model for object detection and semantic segmentation, but only using RGB. This work extends it for Lidar and evaluates performance on KITTI, a public autonomous driving dataset. The implementation shows improved precision across all objects of different sizes. The implementation is entirely made available: https://github.com/filipepcampos/yolomm.

Teses
supervisionadas

2022

Análise e Monitorização do Desempenho do Serviço de Arquivo do Centro Hospitalar Universitário de São João

Autor
Teresa Alexandra Magalhães Campos

Instituição
UP-FEUP

2022

Self-explanatory computer-aided diagnosis with limited supervision

Autor
Isabel Cristina Rio-Torto de Oliveira

Instituição
UP-FEUP

2022

Neuroblastoma Cancer Radiogenomics

Autor
Mafalda Malafaia Baptista de Oliveira

Instituição
UP-FEUP

2022

Application of a Central Battery Energy Storage for a Community Microgrid

Autor
Conceição Cristina Ferreira Pereira

Instituição
UP-FEUP

2022

Multimodal Cervical Cancer Diagnosis: Deep Learning for Automatic Decision Support

Autor
Tomé Mendes Albuquerque

Instituição
UP-FEUP