CLCC: Contrastive Learning for Color Constancy

TL;DR

This paper introduces CLCC, a contrastive learning framework for color constancy that leverages novel raw-domain augmentations to improve illuminant-dependent feature learning, achieving state-of-the-art results efficiently.

Contribution

The paper proposes a new contrastive learning approach with raw-domain color augmentation tailored for color constancy, outperforming existing methods with fewer parameters.

Findings

17.5% relative improvement on NUS-8 dataset

State-of-the-art performance without increasing model complexity

28.7% reduction in worst-case error in data-sparse regions

Abstract

In this paper, we present CLCC, a novel contrastive learning framework for color constancy. Contrastive learning has been applied for learning high-quality visual representations for image classification. One key aspect to yield useful representations for image classification is to design illuminant invariant augmentations. However, the illuminant invariant assumption conflicts with the nature of the color constancy task, which aims to estimate the illuminant given a raw image. Therefore, we construct effective contrastive pairs for learning better illuminant-dependent features via a novel raw-domain color augmentation. On the NUS-8 dataset, our method provides $17.5\%$ relative improvements over a strong baseline, reaching state-of-the-art performance without increasing model complexity. Furthermore, our method achieves competitive performance on the Gehler dataset with $3\times$ fewer parameters compared to top-ranking deep learning methods. More importantly, we show that our model is more robust to different scenes under close proximity of illuminants, significantly reducing $28.7\%$ worst-case error in data-sparse regions.