Detailed info PromptMix: Textto-image diffusion models enhance the performance of lightweight networks AuthorsArian Bakhtiarnia, Qi Zhang, and Alexandros IosifidisTitlePromptMix: Textto-image diffusion models enhance the performance of lightweight networksAbstractMany deep learning…
Detailed info Learning distinctive features helps, provably AuthorsFiras Laakom, Jenni Raitoharju, Alexandros Iosifidis and Moncef GabboujTitleLearning distinctive features helps, provablyAbstractWe study the diversity of the features learned by a two-layer…
Detailed info Large Deviations Rates for Stochastic Gradient Descent with Strongly Convex Functions Authors D. Bajovic, D. Jakovetic, and S. Kar Title Large Deviations Rates for Stochastic Gradient Descent with…
Detailed info One-shot Federated Learning for Model Clustering and Learning in Heterogeneous Environments AuthorsA. Armacki, D. Bajovic, D. Jakovetic and S. KarTitleOne-shot Federated Learning for Model Clustering and Learning in…
Detailed info Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition AuthorsAlessandro Conti, Paolo Rota, Yiming Wang, Elisa RicciTitleCluster-level pseudo-labelling for source-free cross-domain facial expression recognitionAbstractAutomatically understanding emotions from visual data…
Detailed info ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing AuthorsGiulio Mattolin, Luca Zanella, Elisa Ricci, Yiming WangTitleConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based MixingAbstractUnsupervised Domain…
he Internet of Things (IoT) and smart city paradigm includes ubiquitous technology to extract context information in order to return useful services to users and citizens. An essential role in this scenario is often played by computer vision applications, requiring the acquisition of images from specific devices.
