Sanity checks for patch visualisation in prototype-based image classification.
CVPR Workshops(2023)
摘要
In this work, we perform an analysis of the visualisation methods implemented
in ProtoPNet and ProtoTree, two self-explaining visual classifiers based on
prototypes. We show that such methods do not correctly identify the regions of
interest inside of the images, and therefore do not reflect the model
behaviour, which can create a false sense of bias in the model. We also
demonstrate quantitatively that this issue can be mitigated by using other
saliency methods that provide more faithful image patches.
更多查看译文
关键词
faithful image patches,model behaviour,patch visualisation,prototype-based image classification,prototypes,saliency methods,sanity checks,visual classifiers,visualisation methods
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要