Pith. sign in

REVIEW 1 cited by

Evaluating the Robustness of Self-Supervised Learning in Medical Imaging

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 2105.06986 v1 pith:CVMR6XTU submitted 2021-05-14 cs.CV

classification cs.CV
keywords learningrobustnessself-supervisedcomparedfully-supervisedimagingmedicalnetworks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Self-supervision has demonstrated to be an effective learning strategy when training target tasks on small annotated data-sets. While current research focuses on creating novel pretext tasks to learn meaningful and reusable representations for the target task, these efforts obtain marginal performance gains compared to fully-supervised learning. Meanwhile, little attention has been given to study the robustness of networks trained in a self-supervised manner. In this work, we demonstrate that networks trained via self-supervised learning have superior robustness and generalizability compared to fully-supervised learning in the context of medical imaging. Our experiments on pneumonia detection in X-rays and multi-organ segmentation in CT yield consistent results exposing the hidden benefits of self-supervision for learning robust feature representations.

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. An autonomous agent for auditing and improving the reliability of clinical AI models

    cs.AI 2025-07 conditional novelty 6.0 of 10

    ModelAuditor is an LLM agent that audits clinical imaging models, selects metrics and shifts, proposes targeted augmentations, and recovers part of the performance lost under real-world distribution shifts.

Pith tools