A
Antonio D'Innocente
Researcher at Sapienza University of Rome
Publications - 17
Citations - 979
Antonio D'Innocente is an academic researcher from Sapienza University of Rome. The author has contributed to research in topics: Domain (software engineering) & Supervised learning. The author has an hindex of 6, co-authored 17 publications receiving 477 citations. Previous affiliations of Antonio D'Innocente include Istituto Italiano di Tecnologia & Polytechnic University of Turin.
Papers
More filters
Proceedings ArticleDOI
Domain Generalization by Solving Jigsaw Puzzles
TL;DR: This model learns the semantic labels in a supervised fashion, and broadens its understanding of the data by learning from self-supervised signals how to solve a jigsaw puzzle on the same images, which helps the network to learn the concepts of spatial correlation while acting as a regularizer for the classification task.
Book ChapterDOI
Domain Generalization with Domain-Specific Aggregation Modules
TL;DR: In this article, the authors propose a deep architecture that maintains separated the information about the available source domains data while at the same time leveraging over generic perceptual information by introducing domain-specific aggregation modules that through an aggregation layer strategy are able to merge generic and specific information in an effective manner.
Posted Content
Domain Generalization by Solving Jigsaw Puzzles.
TL;DR: In this article, the authors apply a similar approach to the task of object recognition across domains: their model learns the semantic labels in a supervised fashion, and broadens its understanding of the data by learning from self-supervised signals how to solve a jigsaw puzzle on the same images.
Proceedings ArticleDOI
Rethinking Domain Generalization Baselines
TL;DR: In this paper, the authors focus on style transfer data augmentation and present how it can be implemented with a simple and inexpensive strategy to improve generalization, and analyze the behavior of current state-of-the-art domain generalization methods when integrated with this augmentation solution.
Posted Content
Domain Generalization with Domain-Specific Aggregation Modules
TL;DR: A deep architecture is proposed that maintains separated the information about the available source domains data while at the same time leveraging over generic perceptual information in an effective manner, reaching the new state of the art in domain generalization.