AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Quasi-Unsupervised Color Constancy

Simone Bianco, Claudio Cusano

CVPR 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 91 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
Add gradient-direction input to grayscale input (ablation)Proposed method trained on Ilsvrc12 · CCmedian angular error (degrees): 2.67 -> 2.23Improved
Add gradient-direction input to grayscale input (ablation)Proposed method trained on Ilsvrc12 · NUSmedian angular error (degrees): 2.24 -> 2.27Hurt
Use gradient directions instead of grayscale (ablation)Proposed method trained on Ilsvrc12 · CCmedian angular error (degrees): 2.67 -> 2.53Improved
Use gradient directions instead of grayscale (ablation)Proposed method trained on Ilsvrc12 · NUSmedian angular error (degrees): 2.24 -> 2.15Improved
Fine-tune with annotated dataset examples (ablation)Proposed method · CCmedian angular error (degrees): 2.23 -> 1.98Improved
Fine-tune with annotated dataset examples (ablation)Proposed method · NUSmedian angular error (degrees): 2.27 -> 1.41Improved

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