Pith. sign in

REVIEW

Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing

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 2209.03268 v1 pith:HGC242AL submitted 2022-09-07 cs.CV

Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing

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

Self-supervised visual representation learning has recently attracted significant research interest. While a common way to evaluate self-supervised representations is through transfer to various downstream tasks, we instead investigate the problem of measuring their interpretability, i.e. understanding the semantics encoded in raw representations. We formulate the latter as estimating the mutual information between the representation and a space of manually labelled concepts. To quantify this we introduce a decoding bottleneck: information must be captured by simple predictors, mapping concepts to clusters in representation space. This approach, which we call reverse linear probing, provides a single number sensitive to the semanticity of the representation. This measure is also able to detect when the representation contains combinations of concepts (e.g., "red apple") instead of just individual attributes ("red" and "apple" independently). Finally, we propose to use supervised classifiers to automatically label large datasets in order to enrich the space of concepts used for probing. We use our method to evaluate a large number of self-supervised representations, ranking them by interpretability, highlight the differences that emerge compared to the standard evaluation with linear probes and discuss several qualitative insights. Code at: {\scriptsize{\url{https://github.com/iro-cp/ssl-qrp}}}.

discussion (0)

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