LE-ProtoPNet is a new few-shot prototypical concept classification framework that combines LoRA expert mixtures, multi-level feature fusion, and a concept discrimination loss to improve interpretable few-shot image classification.
Learning transferable conceptual prototypes for interpretable unsupervised domain adaptation,
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
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts
LE-ProtoPNet is a new few-shot prototypical concept classification framework that combines LoRA expert mixtures, multi-level feature fusion, and a concept discrimination loss to improve interpretable few-shot image classification.