2 papers
cs.CV2024
Conditioned Prompt-Optimization for Continual Deepfake Detection
Francesco Laiti, Benedetta Liberatori, Thomas De Min +1
The rapid advancement of generative models has significantly enhanced the realism and customization of digital content creation. The increasing power of these tools, coupled with t…
cs.CV2023
On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers
Thomas De Min, Massimiliano Mancini, Karteek Alahari +2
State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forget…