AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Multi-Domain Learning for Accurate and Few-Shot Color Constancy

Jin Xiao, Shuhang Gu, Lei Zhang

CVPR 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-grained and cross-domain few-shot baselines · 63 citations (OpenAlex)

Check 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
Share feature extraction and illuminant estimation across cameras, while using camera-specific channel re-weighting (ablation)FC4-based color constancy · Gehler-Shimean angular error (°): 1.66 -> 1.59Improved
Share feature extraction and illuminant estimation across cameras, while using camera-specific channel re-weighting (ablation)FC4-based color constancy · NUS-C600Dmean angular error (°): 1.97 -> 1.65Improved
Combine device datasets without camera-specific channel re-weighting (ablation)FC4-based color constancy · Gehler-Shimean angular error (°): 1.66 -> 1.87Hurt
Combine device datasets without camera-specific channel re-weighting (ablation)FC4-based color constancy · Cube+mean angular error (°): 1.35 -> 1.36No clear effect
Add camera-specific channel re-weighting to the shared model (ablation)Multi-device Combination · Cube+mean angular error (°): 1.36 -> 1.24Improved
Increase the number of devices used for multi-domain training (ablation)MDLCC · NUS-C600Dmean angular error (°): 1.82 -> 1.65Improved
Increase few-shot adaptation data from K=1 to K=20 (ablation)MDLCC · Cube few-shotmean angular error (°): 2.02 -> 1.47Improved
Adapt only camera-specific parameters using few-shot samples instead of fine-tuning all network weightsFew-shot color constancy · Cube few-shot, K=10mean angular error (°): 1.63 -> 1.56Improved
Adapt only camera-specific parameters using few-shot samples instead of fine-tuning all network weightsFew-shot color constancy · Gehler-Shi few-shot, K=10mean angular error (°): 2.66 -> 2.32Improved

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