5 citations · 5 across the 4 of their papers we have counts for
10 papers · 1 filter
Exploring Data Aggregation and Transformations to Generalize across Visual Domains
Antono D'Innocente
Computer vision has flourished in recent years thanks to Deep Learning advancements, fast and scalable hardware solutions and large availability of structured image data. Convoluti…
Self-Supervision & Meta-Learning for One-Shot Unsupervised Cross-Domain Detection
F. Cappio Borlino, S. Polizzotto, B. Caputo +1
Deep detection approaches are powerful in controlled conditions, but appear brittle and fail when source models are used off-the-shelf on unseen domains. Most of the existing works…
Rethinking Domain Generalization Baselines
Francesco Cappio Borlino, Antonio D'Innocente, Tatiana Tommasi
Despite being very powerful in standard learning settings, deep learning models can be extremely brittle when deployed in scenarios different from those on which they were trained.…
Self-Supervised Learning Across Domains
Silvia Bucci, Antonio D'Innocente, Yujun Liao +3
Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the childr…
One-Shot Unsupervised Cross-Domain Detection
Antonio D'Innocente, Francesco Cappio Borlino, Silvia Bucci +2
Despite impressive progress in object detection over the last years, it is still an open challenge to reliably detect objects across visual domains. Although the topic has attracte…
Learning to Generalize One Sample at a Time with Self-Supervision
Antonio D'Innocente, Silvia Bucci, Barbara Caputo +1
Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is n…
Tackling Partial Domain Adaptation with Self-Supervision
Silvia Bucci, Antonio D'Innocente, Tatiana Tommasi
Domain adaptation approaches have shown promising results in reducing the marginal distribution difference among visual domains. They allow to train reliable models that work over…
Domain Generalization by Solving Jigsaw Puzzles
Fabio Maria Carlucci, Antonio D'Innocente, Silvia Bucci +2
Human adaptability relies crucially on the ability to learn and merge knowledge both from supervised and unsupervised learning: the parents point out few important concepts, but th…
Domain Generalization with Domain-Specific Aggregation Modules
Antonio D'Innocente, Barbara Caputo
Visual recognition systems are meant to work in the real world. For this to happen, they must work robustly in any visual domain, and not only on the data used during training. Wit…
Bridging between Computer and Robot Vision through Data Augmentation: a Case Study on Object Recognition
Antonio D'Innocente, Fabio Maria Carlucci, Mirco Colosi +1
Despite the impressive progress brought by deep network in visual object recognition, robot vision is still far from being a solved problem. The most successful convolutional archi…