no code implementations • 30 Mar 2023 • Simone Rossetti, Nico Samà, Fiora Pirri
Our model attains state-of-the-art in Weakly Supervised Semantic Segmentation, only image-level labels, with 75% mIoU on PascalVOC2012 val set and 46% on MS-COCO2014 val set.
1 code implementation • 31 Oct 2022 • Simone Rossetti, Damiano Zappia, Marta Sanzari, Marco Schaerf, Fiora Pirri
On the other hand, WSSS methods based on Vision Transformers (ViT) have not yet explored valid alternatives to CAM.