Pith. sign in

REVIEW

Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles

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 2110.10293 v1 pith:BQHIY3G6 submitted 2021-10-19 cs.LG cs.CV

classification cs.LGcs.CV
keywords learningmodelrepresentationsself-supervisedensemblingimprovesmodelsperformance
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Pretraining convolutional neural networks via self-supervision, and applying them in transfer learning, is an incredibly fast-growing field that is rapidly and iteratively improving performance across practically all image domains. Meanwhile, model ensembling is one of the most universally applicable techniques in supervised learning literature and practice, offering a simple solution to reliably improve performance. But how to optimally combine self-supervised models to maximize representation quality has largely remained unaddressed. In this work, we provide a framework to perform self-supervised model ensembling via a novel method of learning representations directly through gradient descent at inference time. This technique improves representation quality, as measured by k-nearest neighbors, both on the in-domain dataset and in the transfer setting, with models transferable from the former setting to the latter. Additionally, this direct learning of feature through backpropagation improves representations from even a single model, echoing the improvements found in self-distillation.

Discussion (0). Continue with ORCID to comment.

Pith tools