PETALface adapts pre-trained face-recognition models to low-resolution images by blending two image-quality-weighted LoRA modules, improving low-res benchmarks while preserving high-res accuracy with 0.48% trainable parameters.
Cr-fiqa: face image quality assessment by learning sample relative classifiability
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PETALface: Parameter Efficient Transfer Learning for Low-resolution Face Recognition
PETALface adapts pre-trained face-recognition models to low-resolution images by blending two image-quality-weighted LoRA modules, improving low-res benchmarks while preserving high-res accuracy with 0.48% trainable parameters.