Pith. sign in

REVIEW 3 cited by

Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation

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 2107.12585 v2 pith:7T5EKBNT submitted 2021-07-27 cs.CV cs.AI

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

In the classic setting of unsupervised domain adaptation (UDA), the labeled source data are available in the training phase. However, in many real-world scenarios, owing to some reasons such as privacy protection and information security, the source data is inaccessible, and only a model trained on the source domain is available. This paper proposes a novel deep clustering method for this challenging task. Aiming at the dynamical clustering at feature-level, we introduce extra constraints hidden in the geometric structure between data to assist the process. Concretely, we propose a geometry-based constraint, named semantic consistency on the nearest neighborhood (SCNNH), and use it to encourage robust clustering. To reach this goal, we construct the nearest neighborhood for every target data and take it as the fundamental clustering unit by building our objective on the geometry. Also, we develop a more SCNNH-compliant structure with an additional semantic credibility constraint, named semantic hyper-nearest neighborhood (SHNNH). After that, we extend our method to this new geometry. Extensive experiments on three challenging UDA datasets indicate that our method achieves state-of-the-art results. The proposed method has significant improvement on all datasets (as we adopt SHNNH, the average accuracy increases by over 3.0% on the large-scaled dataset). Code is available at https://github.com/tntek/N2DCX.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection

    cs.CV 2026-07 reject novelty 5.0 of 10

    OKR beats exemplar-free domain-incremental detectors by 5.6–6.5 mAP using per-domain LoRA branches plus gradient orthogonality and prototype alignment.

  2. Grad-CL: Source Free Domain Adaptation with Gradient Guided Feature Disalignment

    cs.CV 2025-09 conditional novelty 4.0 of 10

    Grad-CL uses Grad-CAM features for pseudo-label refinement and a cosine contrastive loss to disalign optic cup and disc features, reporting improved segmentation results.

  3. 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