2 papers
cs.CV2025
Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives
Nikolaos Giakoumoglou, Nikos Giakoumoglou, Andreas Floros +2
This paper does not introduce a new method per se. Instead, we build on existing self-supervised learning approaches for vision, drawing inspiration from the adage "fake it till yo…
cs.CV2025
Unsupervised Training of Vision Transformers with Synthetic Negatives
Nikolaos Giakoumoglou, Nikos Giakoumoglou, Andreas Floros +2
This paper does not introduce a novel method per se. Instead, we address the neglected potential of hard negative samples in self-supervised learning. Previous works explored synth…