Pith. sign in

REVIEW 1 cited by

Self-Supervised Models are Continual Learners

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 2112.04215 v2 pith:T6XHEKLT submitted 2021-12-08 cs.CV cs.LG

classification cs.CVcs.LG
keywords self-supervisedcontinualmodelsrepresentationsdatalearningstatevisual
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Self-supervised models have been shown to produce comparable or better visual representations than their supervised counterparts when trained offline on unlabeled data at scale. However, their efficacy is catastrophically reduced in a Continual Learning (CL) scenario where data is presented to the model sequentially. In this paper, we show that self-supervised loss functions can be seamlessly converted into distillation mechanisms for CL by adding a predictor network that maps the current state of the representations to their past state. This enables us to devise a framework for Continual self-supervised visual representation Learning that (i) significantly improves the quality of the learned representations, (ii) is compatible with several state-of-the-art self-supervised objectives, and (iii) needs little to no hyperparameter tuning. We demonstrate the effectiveness of our approach empirically by training six popular self-supervised models in various CL settings.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Continual Learning-Based Unified Model for Unpaired Image Restoration Tasks

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A continual learning extension of AGLC-GAN that adds selective kernel fusion, cycle-contrastive loss, and EWC to handle unpaired dehazing, desnowing, and deraining in one model.

Pith tools