Learning (Scene and Object Recognition) from Few Examples 6a.006.TUT

Project Start Date: Jul 1, 2017
Research Areas: Analytics, Analytics - Deep Learning, Analytics - Machine Learning, Analytics - Probabilistic Modeling, Analytics - Signal Processing, Analytics - Video Analytics, Data Management, Data Management - Big Data Platforms, Visualization, Visualization - Mobile Computing
Funding: Member Funded
Project Tags: ,

Project Summary

Deep neural networks enable the color constancy algorithms to approximate the function for illuminant estimation. However, the image data required for learning the chromaticity of the illumination remains scarce. Autoencoders provide a promising paradigm to exploit the underlying structure of chromaticity of images by learning over large numbers of unlabeled Internet images, so that we can achieve a good illuminant estimation over new images. We introduce a novel color constancy algorithm by auto-encoding a large dataset of images and using the model to estimate the illumination. We use two approaches. In the first, we learn a common representation of images and then fine-tune the model to estimate the illumination and, in the second approach, we combine the two steps into one using a composite objective function to allow us to learn to reconstruct and, at the same time, regress to the illumination.