Sanity Checks for Saliency Maps

📖 Description

Sanity Checks for Saliency Maps Julius Adebayo, Justin Gilmer], Michael Muelly], Ian Goodfellow], Moritz Hardt]y, Been Kim] [email removed] ,{gilmer,muelly,goodfellow,mrtz,beenkim}@google.com ]Google Brain yUniversity of California Berkeley Abstract Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed, often guided by visual appeal on image data. In this work, we propose an actionable methodology to evaluate what kinds of explanations a given method can and cannot provide. We ?nd that reliance, solely, on visual assessment can be misleading. Through extensive experiments we show that some existing saliency methods are independent both of the model and of the data generating process. Consequently, methods that fail the proposed tests are inadequate for tasks that are sensitive to either data or model, such as, ?nding outliers in the data, explaining the re...

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://arxiv.org/abs/1810.03292