Picture for Roberto Amoroso

Roberto Amoroso

Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation

Add code
Apr 09, 2024
Viaarxiv icon

Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training

Add code
Jun 12, 2023
Viaarxiv icon

Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images

Add code
Apr 02, 2023
Viaarxiv icon