AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment

Heliang Zheng, Huan Yang, Jianlong Fu, Zheng-Jun Zha, Jiebo Luo

ICCV 2021 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment · 73 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
add conditional knowledge distillation (CKD) loss (ablation)CKDN · PIPAL subset (50 train / 39 val IR algorithms)SRCC: 0.7127 -> 0.7549Improved
add relative score regression pre-training (ablation)CKDN · PIPAL subset (50 train / 39 val IR algorithms)SRCC: 0.7549 -> 0.7669Improved
use unshared DTE and QSE embeddings instead of shared (ablation)CKDN · PIPAL subset (50 train / 39 val IR algorithms)SRCC: 0.7311 -> 0.7669Improved
keep full 72x72 feature resolution for CSP input instead of 36x36 (ablation)CKDN · PIPAL subset (50 train / 39 val IR algorithms)SRCC: 0.7436 -> 0.7669Improved
keep full 72x72 feature resolution instead of 18x18 (ablation)CKDN · PIPAL subset (50 train / 39 val IR algorithms)SRCC: 0.7234 -> 0.7669Improved
use residual blocks instead of VGG blocks (ablation)CKDN · PIPAL subset (50 train / 39 val IR algorithms)SRCC: 0.7006 -> 0.7127No clear effect
use conditional KD instead of vanilla knowledge distillation (ablation)CKDN · PIPAL subset (50 train / 39 val IR algorithms)SRCC: 0.7338 -> 0.7669Improved
use conditional KD instead of data augmentation (ablation)CKDN · PIPAL subset (50 train / 39 val IR algorithms)SRCC: 0.7469 -> 0.7669Improved
use conditional KD instead of hallucinated reference (ablation)CKDN · PIPAL subset (50 train / 39 val IR algorithms)SRCC: 0.7348 -> 0.7669Improved
pre-train with relative score regression instead of absolute score regression (10 epochs) (ablation)CKDN · PIPAL subset (50 train / 39 val IR algorithms)SRCC: 0.7536 -> 0.7669Improved
pre-train with relative score regression instead of ImageNet pre-training only (ablation)CKDN · PIPAL subset (50 train / 39 val IR algorithms)SRCC: 0.7549 -> 0.7669Improved
add CKDN as loss term to ESRGAN instead of VGG perceptual lossESRGAN · DIV8K SR (ESRGAN)LPIPS: 0.5039 -> 0.4957Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy