Pith. sign in

REVIEW 2 cited by

Self-supervised learning with rotation-invariant kernels

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 2208.00789 v4 pith:SG6OKDEP submitted 2022-07-28 cs.CV cs.AI

classification cs.CVcs.AI
keywords methodsself-supervisedkernelslearningdistributionembeddinglossregularization
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce a regularization loss based on kernel mean embeddings with rotation-invariant kernels on the hypersphere (also known as dot-product kernels) for self-supervised learning of image representations. Besides being fully competitive with the state of the art, our method significantly reduces time and memory complexity for self-supervised training, making it implementable for very large embedding dimensions on existing devices and more easily adjustable than previous methods to settings with limited resources. Our work follows the major paradigm where the model learns to be invariant to some predefined image transformations (cropping, blurring, color jittering, etc.), while avoiding a degenerate solution by regularizing the embedding distribution. Our particular contribution is to propose a loss family promoting the embedding distribution to be close to the uniform distribution on the hypersphere, with respect to the maximum mean discrepancy pseudometric. We demonstrate that this family encompasses several regularizers of former methods, including uniformity-based and information-maximization methods, which are variants of our flexible regularization loss with different kernels. Beyond its practical consequences for state-of-the-art self-supervised learning with limited resources, the proposed generic regularization approach opens perspectives to leverage more widely the literature on kernel methods in order to improve self-supervised learning methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Maximally Separated Active Learning

    cs.LG 2024-11 conditional novelty 5.0 of 10

    MSAL scores uncertainty by cosine similarity to fixed equiangular class prototypes, and MSAL-D adds prototype-based diversity, reporting improved AUBC on MNIST, SVHN, and TinyImageNet.

  2. Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization

    cs.LG 2024-11 conditional novelty 5.0 of 10

    Continuing SSL pre-training for ten epochs with a criterion that maximizes one-dimensional marginal entropies and minimizes pairwise covariances improves downstream ImageNet classification, especially with few labels.

Pith tools