Color Constancy Convolutional Autoencoder
This work addresses data scarcity in color constancy for computer vision applications, but it is incremental as it builds on existing autoencoder methods.
The paper tackles the color constancy problem by proposing unsupervised and semi-supervised pre-training methods using convolutional autoencoders to address data scarcity, achieving competitive state-of-the-art results with fewer parameters on the ColorChecker RECommended dataset and studying over-fitting on the INTEL-TUT dataset.
In this paper, we study the importance of pre-training for the generalization capability in the color constancy problem. We propose two novel approaches based on convolutional autoencoders: an unsupervised pre-training algorithm using a fine-tuned encoder and a semi-supervised pre-training algorithm using a novel composite-loss function. This enables us to solve the data scarcity problem and achieve competitive, to the state-of-the-art, results while requiring much fewer parameters on ColorChecker RECommended dataset. We further study the over-fitting phenomenon on the recently introduced version of INTEL-TUT Dataset for Camera Invariant Color Constancy Research, which has both field and non-field scenes acquired by three different camera models.