3 papers
cs.CV2026
Multimodal Taxonomic Conditioning for Generative Plankton Imagery
Daniela Ivanova, Ozgu Goksu, Nicolas Pugeault
Automated plankton imaging produces severely long-tailed datasets, where the rare taxa of greatest ecological interest have too few images to train or evaluate classifiers reliably…
cs.LG2026
Enhancing Federated Quadruplet Learning: Stochastic Client Selection and Embedding Stability Analysis
Ozgu Goksu, Nicolas Pugeault
Federated Learning (FL) enables decentralised model training across distributed clients without requiring data centralisation. However, the generalisation performance of the global…
cs.LG2025
FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity
Ozgu Goksu, Nicolas Pugeault
Federated Learning (FL) provides decentralised model training, which effectively tackles problems such as distributed data and privacy preservation. However, the generalisation of…