Pith. sign in

REVIEW 1 cited by

Explainable Image Classification with Evidence Counterfactual

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2004.07511 v1 pith:AMMAGJU7 submitted 2020-04-16 cs.LG cs.AIcs.CV

classification cs.LGcs.AIcs.CV
keywords classificationimagecounterfactualexplanationimportancemethodsmodelobtain
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The complexity of state-of-the-art modeling techniques for image classification impedes the ability to explain model predictions in an interpretable way. Existing explanation methods generally create importance rankings in terms of pixels or pixel groups. However, the resulting explanations lack an optimal size, do not consider feature dependence and are only related to one class. Counterfactual explanation methods are considered promising to explain complex model decisions, since they are associated with a high degree of human interpretability. In this paper, SEDC is introduced as a model-agnostic instance-level explanation method for image classification to obtain visual counterfactual explanations. For a given image, SEDC searches a small set of segments that, in case of removal, alters the classification. As image classification tasks are typically multiclass problems, SEDC-T is proposed as an alternative method that allows specifying a target counterfactual class. We compare SEDC(-T) with popular feature importance methods such as LRP, LIME and SHAP, and we describe how the mentioned importance ranking issues are addressed. Moreover, concrete examples and experiments illustrate the potential of our approach (1) to obtain trust and insight, and (2) to obtain input for model improvement by explaining misclassifications.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Model-Free Counterfactual Subset Selection at Scale

    cs.LG 2025-02 reject novelty 4.0 of 10

    A one-pass streaming algorithm selects a diverse, relevant subset of real examples as counterfactual explanations, with a claimed 1/5.585 approximation guarantee and O(log k) update time.

Pith tools