Pith. sign in

REVIEW 4 cited by

Casting a BAIT for Offline and Online Source-free Domain Adaptation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2010.12427 v5 pith:IKBXQIPO submitted 2020-10-23 cs.CV

Shiqi Yang , Yaxing Wang , Joost van de Weijer , Luis Herranz , Shangling Jui This is my paper · ORCID
classification cs.CV
keywords domainadaptationclassifiertargetsfdasource-freemethodsoffline
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We address the source-free domain adaptation (SFDA) problem, where only the source model is available during adaptation to the target domain. We consider two settings: the offline setting where all target data can be visited multiple times (epochs) to arrive at a prediction for each target sample, and the online setting where the target data needs to be directly classified upon arrival. Inspired by diverse classifier based domain adaptation methods, in this paper we introduce a second classifier, but with another classifier head fixed. When adapting to the target domain, the additional classifier initialized from source classifier is expected to find misclassified features. Next, when updating the feature extractor, those features will be pushed towards the right side of the source decision boundary, thus achieving source-free domain adaptation. Experimental results show that the proposed method achieves competitive results for offline SFDA on several benchmark datasets compared with existing DA and SFDA methods, and our method surpasses by a large margin other SFDA methods under online source-free domain adaptation setting.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Energy-Based Pseudo-Label Refining for Source-free Domain Adaptation

    cs.CV 2025-04 conditional novelty 5.0 of 10

    Energy-based pseudo-label refining with adaptive global/class thresholds and contrastive consistency training improves source-free domain adaptation accuracy on Office-31, Office-Home, and VisDA-C.

  2. DRIVE: Dual-Robustness via Information Variability and Entropic Consistency in Source-Free Unsupervised Domain Adaptation

    cs.CV 2024-11 reject novelty 4.0 of 10

    DRIVE adapts a classifier to an unlabeled target domain by running two model copies with PGD perturbations and entropy-weighted pseudo-labels, reporting small accuracy gains over DIFO on three benchmarks.

  3. Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning

    cs.CV 2024-11 conditional novelty 4.0 of 10

    StepSPT adapts frozen pre-trained models to new domains by learning a style prompt through step-wise distribution alignment plus classifier updates, improving source-free cross-domain few-shot accuracy.

  4. Source-Free Domain Adaptation via Multi-view Contrastive Learning

    cs.CV 2025-07 reject novelty 3.0 of 10

    A three-phase SFUDA method claims state-of-the-art accuracy on VisDA-2017, Office-Home, and Office-31, but the evidence is internally inconsistent.

Pith tools