Pith. sign in

REVIEW

Finding Representative Interpretations on Convolutional Neural Networks

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 2108.06384 v3 pith:YU77BEQC submitted 2021-08-13 cs.CV

Finding Representative Interpretations on Convolutional Neural Networks

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

Interpreting the decision logic behind effective deep convolutional neural networks (CNN) on images complements the success of deep learning models. However, the existing methods can only interpret some specific decision logic on individual or a small number of images. To facilitate human understandability and generalization ability, it is important to develop representative interpretations that interpret common decision logics of a CNN on a large group of similar images, which reveal the common semantics data contributes to many closely related predictions. In this paper, we develop a novel unsupervised approach to produce a highly representative interpretation for a large number of similar images. We formulate the problem of finding representative interpretations as a co-clustering problem, and convert it into a submodular cost submodular cover problem based on a sample of the linear decision boundaries of a CNN. We also present a visualization and similarity ranking method. Our extensive experiments demonstrate the excellent performance of our method.

discussion (0)

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