Researchers have developed GRAM, a novel framework for image quality assessment (IQA) that draws inspiration from psychometric graded response models. This approach models quality judgments based on latent quality, content-dependent response sensitivity, and distortion-dependent grade thresholds. Experiments across nine datasets show that GRAM improves coreset selection strategies and downstream IQA models, even with limited annotation budgets. The framework's code is slated for public release. AI
IMPACT This framework could improve the efficiency of training AI models for image quality assessment by reducing the need for extensive manual annotation.
RANK_REASON The cluster contains a research paper detailing a new framework for image quality assessment. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- DagsHub
- Gotit.pub
- Graded Response Model (GRM)
- GRAM
- Hugging Face
- image quality assessment (IQA)
- ScienceCast
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →