ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts
This work addresses the need for interpretability in semantic segmentation for computer vision applications, though it appears incremental as it builds on existing prototypical part mechanisms.
The paper tackles the problem of making semantic image segmentation interpretable by introducing ProtoSeg, a model that uses prototypical parts and a diversity loss to achieve accuracy comparable to baseline methods while discovering semantic concepts. Experiments on Pascal VOC and Cityscapes datasets confirm its precision and transparency.
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.