6 papers
Neural Collapse by Design: Learning Class Prototypes on the Hypersphere
Panagiotis Koromilas, Theodoros Giannakopoulos, Mihalis A. Nicolaou +1
Supervised classification has a theoretical optimum, Neural Collapse (NC), yet neither of its two dominant paradigms reaches it in practice. Cross entropy (CE) leaves radial degree…
REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
Giorgos Petsangourakis, Christos Sgouropoulos, Bill Psomas +3
Latent diffusion models (LDMs) achieve state-of-the-art image synthesis, yet their reconstruction-style denoising objective provides only indirect semantic supervision: high-level…
Prototypical Contrastive Learning For Improved Few-Shot Audio Classification
Christos Sgouropoulos, Christos Nikou, Stefanos Vlachos +3
Few-shot learning has emerged as a powerful paradigm for training models with limited labeled data, addressing challenges in scenarios where large-scale annotation is impractical.…
A Principled Framework for Multi-View Contrastive Learning
Panagiotis Koromilas, Efthymios Georgiou, Giorgos Bouritsas +3
Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentation…
Contrastive and Transfer Learning for Effective Audio Fingerprinting through a Real-World Evaluation Protocol
Christos Nikou, Theodoros Giannakopoulos
Recent advances in song identification leverage deep neural networks to learn compact audio fingerprints directly from raw waveforms. While these methods perform well under control…
Greek2MathTex: A Greek Speech-to-Text Framework for LaTeX Equations Generation
Evangelia Gkritzali, Panagiotis Kaliosis, Sofia Galanaki +2
In the vast majority of the academic and scientific domains, LaTeX has established itself as the de facto standard for typesetting complex mathematical equations and formulae. Howe…