Artificial Color Constancy via GoogLeNet with Angular Loss Function
This addresses color constancy for machines to improve scene understanding and object recognition in fields using chromatic information, but it appears incremental as it builds on existing CNNs.
The paper tackled color constancy by proposing a transfer learning-based algorithm using GoogLeNet with a new angular loss function, achieving higher accuracy than many state-of-the-art methods and emphasizing simplicity of implementation.
Color Constancy is the ability of the human visual system to perceive colors unchanged independently of the illumination. Giving a machine this feature will be beneficial in many fields where chromatic information is used. Particularly, it significantly improves scene understanding and object recognition. In this paper, we propose transfer learning-based algorithm, which has two main features: accuracy higher than many state-of-the-art algorithms and simplicity of implementation. Despite the fact that GoogLeNet was used in the experiments, given approach may be applied to any CNN. Additionally, we discuss design of a new loss function oriented specifically to this problem, and propose a few the most suitable options.