CLCC: Contrastive Learning for Color Constancy

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.

Accepted at CVPR 2021. Our code is available at https://github.com/howardyclo/clcc-cvpr21

References in corpus (5)

• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• On Variational Bounds of Mutual Information
• APAC: Augmented PAttern Classification with Neural Networks
• Data Augmentation in Emotion Classification Using Generative Adversarial Networks
• Noise or Signal: The Role of Image Backgrounds in Object Recognition