🧪 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
1h ago70%
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.