GNN-ViTCap combines deep embedded clustering, graph-based aggregation, and large language models to classify and caption microscopic whole slide images, reporting high F1, AUC, BLEU, and METEOR scores on BreakHis and PatchGastric.
Attention-based deep multiple instance learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning
GNN-ViTCap combines deep embedded clustering, graph-based aggregation, and large language models to classify and caption microscopic whole slide images, reporting high F1, AUC, BLEU, and METEOR scores on BreakHis and PatchGastric.