5 citations · 5 across the 4 of their papers we have counts for
3 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.…