ProtoSeg: Interpretable Semantic Segmentation With Prototypical Parts

Mikołaj Sacha, Dawid Rymarczyk, Łukasz Struski, Jacek Tabor, Bartosz Zieliński; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023, pp. 1481-1492

Abstract

We introduce ProtoSeg, a novel model for interpretable semantic image segmentation, which constructs its predictions using similar patches from the training set. To achieve accuracy comparable to baseline methods, we adapt the mechanism of prototypical parts and introduce a diversity loss function that increases the variety of prototypes within each class. We show that ProtoSeg discovers semantic concepts, in contrast to standard segmentation models. Experiments conducted on Pascal VOC and Cityscapes datasets confirm the precision and transparency of the presented method.

Related Material

[pdf] [supp]
[bibtex]
@InProceedings{Sacha_2023_WACV, author = {Sacha, Miko{\l}aj and Rymarczyk, Dawid and Struski, {\L}ukasz and Tabor, Jacek and Zieli\'nski, Bartosz}, title = {ProtoSeg: Interpretable Semantic Segmentation With Prototypical Parts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2023}, pages = {1481-1492} }