CLCC: Contrastive Learning for Color Constancy
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021(2021)
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 3x 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% worstcase error in data-sparse regions. Our code is available at https://github. coin/ howardyclo/cicc-cvpr21.
MoreTranslated text
Key words
contrastive learning framework,high-quality visual representations,image classification,illuminant invariant augmentations,illuminant invariant assumption conflicts,color constancy task,effective contrastive pairs,illuminant-dependent features,NUS-8 dataset,top-ranking deep learning methods,raw-domain color augmentation,Contrastive Learning for Color Constancy
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined