4 papers
Authentication of Copy Detection Patterns via Cross-Camera Dual-Synthetic Referencing
Ivan Oleksiyuk, Roman Chaban, Slava Voloshynovskiy
Copy Detection Patterns (CDPs) are structures printed on physical objects to enable cost-effective authentication. Verification is achieved by comparing a captured image with the d…
Human-Inspired Context-Selective Multimodal Memory for Social Robots
Hangyeol Kang, Slava Voloshynovskiy, Nadia Magnenat Thalmann
Memory is fundamental to social interaction, enabling humans to recall meaningful past experiences and adapt their behavior accordingly based on the context. However, most current…
TwinTURBO: Semi-Supervised Fine-Tuning of Foundation Models via Mutual Information Decompositions for Downstream Task and Latent Spaces
Guillaume Quétant, Pavlo Molchanov, Slava Voloshynovskiy
We present a semi-supervised fine-tuning framework for foundation models that utilises mutual information decomposition to address the challenges of training for a limited amount o…
Robustness Tokens: Towards Adversarial Robustness of Transformers
Brian Pulfer, Yury Belousov, Slava Voloshynovskiy
Recently, large pre-trained foundation models have become widely adopted by machine learning practitioners for a multitude of tasks. Given that such models are publicly available,…