Papers/2609.21012
🧪 Test?View on arXiv

Fragment-Aware Vision Transformers for Fresco-Fragment Style Classification

Author1, Author2, Author3, Author4, Author5

transformersart classificationcomputer visioncontrastive learning
2609.21012
Builder Relevance
70%
1h ago

Abstract

This paper presents a progressive transformer-based framework for classifying fresco fragments, addressing the challenges posed by incomplete artworks.

Reality Card

Core Claim

The proposed fragment-aware modeling improves classification accuracy from 0.604 to 0.656 on the CLEOPATRA dataset using a simple learnable logit ensemble.

Method / Result

The ensemble method increased macro-F1 from 0.596 to 0.648 on CLEOPATRA.

Limitations

The complexity of the graph-fusion variant does not justify its small gains, which may affect reproducibility in different datasets.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers