Views
No views yet
Key Insight: Given sufficient scale and pretraining, a plain ViT along with additional few params can perform segmentation without the need for task-specific decoders or pixel fusion modules. The same model backbone supports semantic, instance, and panoptic segmentation with different post-processing 🤗
1@inproceedings{kerssies2025eomt,
2 author = {Kerssies, Tommie and Cavagnero, Niccolò and Hermans, Alexander and Norouzi, Narges and Averta, Giuseppe and Leibe, Bastian and Dubbelman, Gijs and de Geus, Daan},
3 title = {Your ViT is Secretly an Image Segmentation Model},
4 booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
5 year = {2025},
6}