Swin Transformer achieves the highest reported accuracy (94% binary, 73% multiclass) on a public thermal PV fault dataset, but the physics-validated interpretability claim rests on qualitative inspection of saliency maps.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Benchmarking Vision Transformers and CNNs for Thermal Photovoltaic Fault Detection with Explainable AI Validation
Swin Transformer achieves the highest reported accuracy (94% binary, 73% multiclass) on a public thermal PV fault dataset, but the physics-validated interpretability claim rests on qualitative inspection of saliency maps.