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.
Abstract (translated)
我们介绍了ProtoSeg,一个可解释语义图像分割的新模型,该模型使用训练集中类似的斑点来构建其预测。为了与基准方法实现相同的精度,我们调整了典型的部分机制,并引入了多样性损失函数,以增加每个类别中的典型的数量。我们表明,ProtoSeg发现了与标准分割模型不同的语义概念。在Pascal VOC和城市景观数据集上的实验确认了本文方法的精度和透明度。
URL
https://arxiv.org/abs/2301.12276