Papers › Sanity Checks for Saliency Maps

Sanity Checks for Saliency Maps

8 Oct 2018NeurIPS 2018 12arXiv:1810.03292archive 2025-07-28

Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim

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 find 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, finding outliers in the data, explaining the relationship between inputs and outputs that the model learned, and debugging the model. We interpret our findings through an analogy with edge detection in images, a technique that requires neither training data nor model. Theory in the case of a linear model and a single-layer convolutional neural network supports our experimental findings.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

adebayoj/sanity_checks_saliency officialtfSyntology: not harvested report
Shubhambindal2017/Unoffical-Implementation-of-GRAD-CAM-with-Sanity-Checks mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization (arXiv:1610.02391; that paper's own run record: 90 ran (of which 32 constructed an object rather than computing a result; 62 with no instrument failure: 6 honoured, 4 violated, 52 with no contract checked; 28 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
annahedstroem/sanity-checks-revisited mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Fresh Look at Sanity Checks for Saliency Maps (arXiv:2405.02383; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
jendawkins/saliencySanity mentioned on GitHubpytorchSyntology: not harvested report
pytorch/captum mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Understanding and Improving Feature Learning for Out-of-Distribution Generalization (arXiv:2304.11327; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Edge DetectionSaliency Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

XGrad-CAM

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections