Research map / Image generation / Autoregressive and latent generation
Data-Efficient Image Quality Assessment with Attention-Panel Decoder
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DEIQT instead of the strongest listed baseline | BIQA methods · LIVE | SRCC: 0.969 -> 0.980 | Helped |
| Use DEIQT instead of the strongest listed baseline | BIQA methods · TID2013 | SRCC: 0.863 -> 0.892 | Helped |
| Use DEIQT instead of the strongest listed baseline | BIQA methods · LIVEC | SRCC: 0.859 -> 0.875 | Helped |
| Use DEIQT instead of the strongest listed baseline | BIQA methods · KonIQ | SRCC: 0.916 -> 0.921 | Helped |
| Use DEIQT instead of the strongest listed baseline | BIQA methods · LIVEFB | SRCC: 0.566 -> 0.571 | Helped |
| Add the quality-aware decoder to ViT (ablation) | DEIQT on LIVEC · LIVEC | SRCC: 0.714 -> 0.863 | Helped |
| Add the quality-aware decoder to ViT (ablation) | DEIQT on KonIQ · KonIQ | SRCC: 0.908 -> 0.918 | Helped |
| Add attention-panel to the decoder-based method (ablation) | DEIQT on LIVEC · LIVEC | SRCC: 0.863 -> 0.875 | Helped |
| Add attention-panel to the decoder-based method (ablation) | DEIQT on KonIQ · KonIQ | SRCC: 0.918 -> 0.921 | Helped |
| Use CLS token rather than random numbers as decoder input (ablation) | DEIQT on LIVEC · LIVEC | SRCC: 0.842 -> 0.863 | Helped |
| Use CLS token rather than random numbers as decoder input (ablation) | DEIQT on KonIQ · KonIQ | SRCC: 0.916 -> 0.918 | Helped |
| Increase decoder depth from 1 to 4 layers (ablation) | DEIQT · LIVEC | SRCC: 0.875 -> 0.877 | No clear effect |
Closest papers by meaning
- Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment (ICML 2024 · similarity 0.89)
- Feature Denoising Diffusion Model for Blind Image Quality Assessment (AAAI 2025 · similarity 0.89)
- Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment (CVPR 2025 · similarity 0.88)
- Towards Syn-to-Real IQA: A Novel Perspective on Reshaping Synthetic Data Distributions (NeurIPS 2025 · similarity 0.87)
- Semi-Supervised Blind Image Quality Assessment through Knowledge Distillation and Incremental Learning (AAAI 2024 · similarity 0.87)
- Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.