TransformAR-KD+ uses knowledge distillation with category-aware teachers and cross-attention decoders to improve AR image quality prediction, achieving SRCC 0.8411 on ARIQA.
Title resolution pending
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
-
Enhancing Content Representation for AR Image Quality Assessment Using Knowledge Distillation
TransformAR-KD+ uses knowledge distillation with category-aware teachers and cross-attention decoders to improve AR image quality prediction, achieving SRCC 0.8411 on ARIQA.