CoChat

Finding and removing Clever Hans: Using explanation methods to debug and improve deep models

Open access
Anders, Christopher J., Weber, Leander, Neumann, David, Samek, Wojciech, Müller, Klaus-Robert, Lapuschkin, Sebastian · 2022 · Information Fusion
Cited by 119

The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.

Abstract

Contemporary learning models for computer vision are typically trained on very large (benchmark) datasets with millions of samples. These may, however, contain biases, artifacts, or errors that have gone unnoticed and are exploitable by the model. In the worst case, the trained model does not learn a valid and generalizable strategy to solve the problem it was trained for, and becomes a “Clever Hans” predictor that bases its decisions on spurious correlations in the training data , potentially yielding an unrepresentative or unfair, and possibly even hazardous predictor. In this paper, we contribute by providing a comprehensive analysis framework based on a scalable statistical analysis of attributions from explanation methods for large data corpora . Based on a recent technique — Spectral Relevance Analysis — we propose the following technical contributions and resulting findings: (a) a scalable quantification of artifactual and poisoned classes where the machine learning models under study exhibit Clever Hans behavior, (b) several approaches we collectively denote as Class Artifact Compensation, which are able to effectively and significantly reduce a model’s Clever Hans behavior, i.e., we are able to un-Hans models trained on (poisoned) datasets, such as the popular ImageNet data corpus. We demonstrate that Class Artifact Compensation, defined in a simple theoretical framework, may be implemented as part of a neural network’s training or fine-tuning process, or in a post-hoc manner by injecting additional layers, preventing any further propagation of undesired Clever Hans features, into the network architecture . Using our proposed methods, we provide qualitative and quantitative analyses of the biases and artifacts in, e.g., the ImageNet dataset, the Adience benchmark dataset of unfiltered faces, and the ISIC 2019 skin lesion analysis dataset. We demonstrate that these insights can give rise to improved, more representative, and fairer models operating on implicitly cleaned data corpora.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.inffus.2021.07.015

Cites

40 of 40 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 40 references

Cited by

See all 119

Metadata

Authors
Anders, C. J., Weber, L., Neumann, D., Samek, W., Müller, K.-R., & Lapuschkin, S.
Venue
Information Fusion
Publisher
Elsevier BV
Published
2022-01
Volume
77
Pages
261-295
ISSN
1566-2535 (ISSN-L)
OpenAlex
W3114162576
Cited by
119
References
40
FWCI
6.26
Type
journal article
Language
en
Open access
hybrid

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Finding and removing Clever Hans: Using explanation methods to debug and improve deep models. https://app.cochat.ai/papers/10.1016/j.inffus.2021.07.015
The paper
Anders, C. J., Weber, L., Neumann, D., Samek, W., Müller, K.-R., & Lapuschkin, S. (2022). Finding and removing Clever Hans: Using explanation methods to debug and improve deep models. Information Fusion. https://doi.org/10.1016/j.inffus.2021.07.015

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.