Pith. sign in

REVIEW

Evaluating the Faithfulness of Saliency-based Explanations for Deep Learning Models for Temporal Colour Constancy

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 2211.07982 v1 pith:INXLFP4X submitted 2022-11-15 cs.CV cs.LG

Evaluating the Faithfulness of Saliency-based Explanations for Deep Learning Models for Temporal Colour Constancy

classification cs.CV cs.LG
keywords faithfulnessmodelsattentiondeepsaliencycolourconstancydecision-making
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The opacity of deep learning models constrains their debugging and improvement. Augmenting deep models with saliency-based strategies, such as attention, has been claimed to help get a better understanding of the decision-making process of black-box models. However, some recent works challenged saliency's faithfulness in the field of Natural Language Processing (NLP), questioning attention weights' adherence to the true decision-making process of the model. We add to this discussion by evaluating the faithfulness of in-model saliency applied to a video processing task for the first time, namely, temporal colour constancy. We perform the evaluation by adapting to our target task two tests for faithfulness from recent NLP literature, whose methodology we refine as part of our contributions. We show that attention fails to achieve faithfulness, while confidence, a particular type of in-model visual saliency, succeeds.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.