Pith. sign in

REVIEW 1 cited by

Contrastive Neighborhood Alignment

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 2201.01922 v1 pith:5PCY2EMF submitted 2022-01-06 cs.LG cs.CV

classification cs.LGcs.CV
keywords modelcontrastivelearningmanifoldspacealignmentdatalocal
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features whereby data points that are mapped to nearby representations by the source (teacher) model are also mapped to neighbors by the target (student) model. The target model aims to mimic the local structure of the source representation space using a contrastive loss. CNA is an unsupervised learning algorithm that does not require ground-truth labels for the individual samples. CNA is illustrated in three scenarios: manifold learning, where the model maintains the local topology of the original data in a dimension-reduced space; model distillation, where a small student model is trained to mimic a larger teacher; and legacy model update, where an older model is replaced by a more powerful one. Experiments show that CNA is able to capture the manifold in a high-dimensional space and improves performance compared to the competing methods in their domains.

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. Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Proxy-FDA aligns the local neighborhood structure of pre-trained and fine-tuned feature spaces, generating synthetic proxies to reduce concept forgetting during fine-tuning.

Pith tools