Niccolò Cavagnero — accepted AI-conference papers

2026

VidEoMT: Your ViT is Secretly Also a Video Segmentation Model

Narges Norouzi, Idil Esen Zulfikar, Niccolò Cavagnero, Tommie Kerssies, Bastian Leibe, Gijs Dubbelman +1

CVPR 2026

Existing online video segmentation models typically combine a per-frame segmenter with complex specialized tracking modules. While effective, these modules introduce significant architectural complexity and computational overhead. Recent studies suggest that plain Vision Transformer (ViT) encoders,

Cited by 0 Source ↗code ↗Scholar ↗

2025

Your ViT is Secretly an Image Segmentation Model

Tommie Kerssies, Niccolò Cavagnero, Alexander Hermans, Narges Norouzi, Giuseppe Averta, Bastian Leibe +2

CVPR 2025highlight

Vision Transformers (ViTs) have shown remarkable performance and scalability across various computer vision tasks. To apply single-scale ViTs to image segmentation, existing methods adopt a convolutional adapter to generate multi-scale features, a pixel decoder to fuse these features, and a Transfor…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2024

PEM: Prototype-based Efficient MaskFormer for Image Segmentation

Niccolò Cavagnero, Gabriele Rosi, Claudia Cuttano, Francesca Pistilli, Marco Ciccone, Giuseppe Averta +1

CVPR 2024poster

Recent transformer-based architectures have shown impressive results in the field of image segmentation. Thanks to their flexibility they obtain outstanding performance in multiple segmentation tasks such as semantic and panoptic under a single unified framework. To achieve such impressive performan…

Cited by 28 Source ↗PDF ↗code ↗Scholar ↗