Monte Carlo Dropout Ensembles for Robust Illumination Estimation
This work addresses robustness in illumination estimation for camera systems, but it is incremental as it builds on existing deep learning approaches.
The paper tackled the problem of high errors in deep learning-based computational color constancy for extreme samples by aggregating methods based on output uncertainty using Monte Carlo dropout, achieving state-of-the-art performance on the INTEL-TAU dataset.
Computational color constancy is a preprocessing step used in many camera systems. The main aim is to discount the effect of the illumination on the colors in the scene and restore the original colors of the objects. Recently, several deep learning-based approaches have been proposed to solve this problem and they often led to state-of-the-art performance in terms of average errors. However, for extreme samples, these methods fail and lead to high errors. In this paper, we address this limitation by proposing to aggregate different deep learning methods according to their output uncertainty. We estimate the relative uncertainty of each approach using Monte Carlo dropout and the final illumination estimate is obtained as the sum of the different model estimates weighted by the log-inverse of their corresponding uncertainties. The proposed framework leads to state-of-the-art performance on INTEL-TAU dataset.