Simone Rossetti, Damiano Zappia, Marta Sanzari, Marco Schaerf, Fiora Pirri. Max Pooling with Vision Transformers Reconciles Class and Shape in Weakly Supervised Semantic Segmentation. In Shai Avidan, Gabriel J. Brostow, Moustapha Cissé, Giovanni Maria Farinella, Tal Hassner, editors, Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXX. Volume 13690 of Lecture Notes in Computer Science, pages 446-463, Springer, 2022. [doi]
Abstract is missing.