PhD Student in Deep Learning @ PoliTO

Publications

My research focuses on distributional shift challenges that arise when moving deep learning based Computer Vision algorithms from training to test conditions. I study visual domain and semantic shifts, which means that my papers touch problems like Domain Adaptation, Domain Generalization, Open Set Recognition and Out-of-distribution detection.

In the following list asterisks* near authors names mean equal contribution.

Conferences

2023


Large Class Separation is not what you need for Relational Reasoning-based OOD Detection
Lorenzo Li Lu, Giulia D’Ascenzi, Francesco Cappio Borlino, and Tatiana Tommasi
In: International Conference on Image Analysis and Processing, ICIAP 2023



2022


Semantic Novelty Detection via Relational Reasoning
Francesco Cappio Borlino*, Silvia Bucci*, and Tatiana Tommasi
In: European Conference on Computer Vision, ECCV 2022



Towards Open Set 3D Learning: Benchmarking and Understanding Semantic Novelty Detection on Pointclouds
Antonio Alliegro*, Francesco Cappio Borlino*, and Tatiana Tommasi
In: Proceedings of the Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks, 2022



Contrastive Learning for Cross-Domain Open World Recognition
Francesco Cappio Borlino, Silvia Bucci, and Tatiana Tommasi
In: The 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)



2021


Rethinking Domain Generalization Baselines
Francesco Cappio Borlino, Antonio D’Innocente, and Tatiana Tommasi
In: 25th International Conference on Pattern Recognition, ICPR 2020



Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation
Silvia Bucci*, Francesco Cappio Borlino*, Barbara Caputo, and Tatiana Tommasi
In: Winter Conference on Applications of Computer Vision, WACV 2022



2020


One-shot unsupervised cross-domain detection
Antonio D’Innocente, Francesco Cappio Borlino, Silvia Bucci, Barbara Caputo, and Tatiana Tommasi
In: European Conference on Computer Vision, ECCV 2020



Domain Generalization vs Data Augmentation: An Unbiased Perspective
Francesco Cappio Borlino, Antonio D’Innocente, and Tatiana Tommasi
In: European Conference on Computer Vision Workshops, ECCV Workshops 2020



Journals


Self-Supervision & Meta-Learning for One-Shot Unsupervised Cross-Domain Detection
Francesco Cappio Borlino, Salvatore Polizzotto, Barbara Caputo, and Tatiana Tommasi
In: Computer Vision and Image Understanding Journal (CVIU), 2022



Preprints

OpenPatch: a 3D patchwork for Out-Of-Distribution detectionpdf icon
Paolo Rabino, Antonio Alliegro, Francesco Cappio Borlino, and Tatiana Tommasi