A Simple Domain Shifting Networkfor Generating Low Quality Images
This addresses the issue of adapting image classifiers for robotics with low-quality cameras, though it is incremental as it builds on existing domain adaptation methods.
The paper tackles the problem of low image quality from cheap cameras in robotics, which reduces classification accuracy, by proposing a network that degrades high-quality images to mimic low-quality systems. The result is that classification networks trained with these degraded images outperform those trained only on high-quality data on a real robot, with the method being easier to use than zero-shot domain adaptation techniques.
Deep Learning systems have proven to be extremely successful for image recognition tasks for which significant amounts of training data is available, e.g., on the famous ImageNet dataset. We demonstrate that for robotics applications with cheap camera equipment, the low image quality, however,influences the classification accuracy, and freely available databases cannot be exploited in a straight forward way to train classifiers to be used on a robot. As a solution we propose to train a network on degrading the quality images in order to mimic specific low quality imaging systems. Numerical experiments demonstrate that classification networks trained by using images produced by our quality degrading network along with the high quality images outperform classification networks trained only on high quality data when used on a real robot system, while being significantly easier to use than competing zero-shot domain adaptation techniques.