PromptMix: Textto-image diffusion models enhance the performance of lightweight networks

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…

Continue ReadingPromptMix: Textto-image diffusion models enhance the performance of lightweight networks

Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition

  • Post category:Publications

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…

Continue ReadingCluster-level pseudo-labelling for source-free cross-domain facial expression recognition

ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing

  • Post category:Publications

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…

Continue ReadingConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing

Low-Complexity Acoustic Scene Classification in DCASE 2022 Challenge publication

  • Post category:Publications

Detailed info Low-Complexity Acoustic Scene Classification in DCASE 2022 Challenge Authors Irene Martín-Morató, Francesco Paissan, Alberto Ancilotto, Toni Heittola, Annamaria Mesaros, Elisabetta Farella, Alessio Brutti, and Tuomas Virtanen Title Low-Complexity…

Continue ReadingLow-Complexity Acoustic Scene Classification in DCASE 2022 Challenge publication