My research in Computer Vision and Machine Learning revolves around the problems of generalization and robustness to changing environments and perturbations of the input data. I focus on identifying and mitigating the sources of bias in training data, while inducing good bias via expert and prior knowledge in the training process, model architectures or labels.

I address the understanding of the training data characteristics and the learning dynamics of computer vision models, to identify sources of bias and counteract them. I investigate the use of prior knowledge, in the form of improved labeling procedures to better exploit data semantics, in the design of novel architectural elements or to steer the learning process (e.g. via physics-informed models) for the training of data-efficient models, taking into account aspects related to training time and energy consumption. I envision efficient and robust computer vision models with embedded prior knowledge that are able to perform unbiased predictions, exploiting the semantics of the data rather than shortcut solutions, with reduced training time, size of the parameter space and energy  consumption, with comparable performance to larger models trained with massive datasets and with higher computational requirements.

Ongoing PhD supervision
Shunxin Wang (University of Twente, Data Management and Biometrics group)
Zohra Rezgui (University of Twente, Data Management and Biometrics group)
Sven Dummer (University of Twente, Mathematics of Imaging and AI group)
Melissa Tijink (University of Twente, Data Management and Biometrics group)
Peter van der Wal (University of Groningen, Information systems group)

Completed PhD supervision
Dr. Maria Leyva Vallina (University of Groningen, The Netherlands - 2023)
Dr. Virginia Riego del Castillo (University of Leon, Spain - 2022)
Dr. Vincenzo Vigilante (University of Salerno, Italy - 2021)

Publications

2024
2023
Quantifying white matter hyperintensity and brain volumes in heterogeneous clinical and low-field portable MRI. ArXiv.org. Laso, P., Cerri, S., Sorby-Adams, A., Guo, J., Mateen, F., Goebl, P., Wu, J., Liu, P., Li, H., Young, S. I., Billot, B., Puonti, O., Sze, G., Payabavash, S., DeHavenon, A., Sheth, K. N., Rosen, M. S., Kirsch, J., Strisciuglio, N., ‚Ķ Iglesias, J. E.https://doi.org/10.48550/arXiv.2312.05119What do neural networks learn in image classification? A frequency shortcut perspectiveIn 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Article 10378114 (pp. 1433-1442). IEEE. Wang, S., Veldhuis, R., Brune, C. & Strisciuglio, N.https://doi.org/10.1109/ICCV51070.2023.00138DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut LearningIn 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Article 10350684 (pp. 129-138). IEEE. Wang, S., Brune, C., Veldhuis, R. & Strisciuglio, N.https://doi.org/10.1109/ICCVW60793.2023.00020DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning. ArXiv.org. Wang, S., Brune, C., Veldhuis, R. & Strisciuglio, N.https://doi.org/10.48550/arXiv.2308.06622Defocus Blur Synthesis and Deblurring via Interpolation and Extrapolation in Latent Space. ArXiv.org. Mazilu, I., Wang, S., Dummer, S., Veldhuis, R., Brune, C. & Strisciuglio, N.https://doi.org/10.48550/arXiv.2307.15461What do neural networks learn in image classification?: A frequency shortcut perspective. ArXiv.org. Wang, S., Veldhuis, R., Brune, C. & Strisciuglio, N.https://doi.org/10.48550/arXiv.2307.09829Data-efficient visual place recognition with graded similarity supervision. Leyva-Vallina, M., Strisciuglio, N. & Petkov, N.https://openaccess.thecvf.com/content/CVPR2023/papers/Leyva-Vallina_Data-Efficient_Large_Scale_Place_Recognition_With_Graded_Similarity_Supervision_CVPR_2023_paper.pdfRSA-INR: Riemannian Shape Autoencoding via 4D Implicit Neural Representations, 1-26. ArXiv.org (Submitted). Dummer, S., Brune, C. & Strisciuglio, N.https://arxiv.org/abs/2305.12854Rda-inr: Riemannian Diffeomorphic Autoencoding via Implicit Neural Representations. ArXiv.org. Dummer, S., Strisciuglio, N. & Brune, C.https://doi.org/10.48550/arXiv.2305.12854A Survey on the Robustness of Computer Vision Models against Common Corruptions. ArXiv.org. Wang, S., Veldhuis, R., Brune, C. & Strisciuglio, N.https://doi.org/10.48550/arXiv.2305.06024Automated assessment of human engineered heart tissues using deep learning and template matching for segmentation and trackingBioengineering and Translational Medicine, 8(3), Article e10513. Rivera-Arbeláez, J. M., Keekstra, D., Cofiño-Fabres, C., Boonen, T., Dostanic, M., ten Den, S. A., Vermeul, K., Mastrangeli, M., van den Berg, A., Segerink, L. I., Ribeiro, M. C., Strisciuglio, N. & Passier, R.https://doi.org/10.1002/btm2.10513

Research profiles

Affiliated study programs

Courses academic year 2023/2024

Courses in the current academic year are added at the moment they are finalised in the Osiris system. Therefore it is possible that the list is not yet complete for the whole academic year.

Courses academic year 2022/2023

Address

University of Twente

Zilverling (building no. 11), room 4122
Hallenweg 19
7522 NH Enschede
Netherlands

Navigate to location

Organisations

Scan the QR code or
Download vCard