Pith. sign in

REVIEW 2 cited by

Test-Time Training with Self-Supervision for Generalization under Distribution Shifts

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 1909.13231 v3 pith:XF2D2IKA submitted 2019-09-29 cs.LG cs.CVstat.ML

classification cs.LGcs.CVstat.ML
keywords trainingapproachdatadistributionshiftstesttest-timeaimed
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised learning problem, on which we update the model parameters before making a prediction. This also extends naturally to data in an online stream. Our simple approach leads to improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts.

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. Feed Two Birds with One Scone: Exploiting Function-Space Regularization for Both OOD Robustness and ID Fine-Tuning Performance

    cs.LG 2025-08 conditional novelty 4.0 of 10

    A CLIP fine-tuning method that penalizes output differences from the pretrained model and prediction differences under augmentation improves both ID accuracy and OOD robustness in reported experiments.

  2. T3DM: Test-Time Training-Guided Distribution Shift Modelling for Temporal Knowledge Graph Reasoning

    cs.AI 2025-07 reject novelty 4.0 of 10

    T3DM couples an LSTM-predicted entity-distribution auxiliary task at test time with a GAN-based negative sampler to improve temporal knowledge graph link prediction.

Pith tools