Image-to-Image Translation of Synthetic Samples for Rare Classes
This work addresses data imbalance for rare classes in wildlife monitoring, but it is incremental as it applies existing translation methods to a specific domain.
The paper tackles the problem of domain shift between synthetic and real imagery in low-shot learning for rare animal species classification, using image-to-image translation to align synthetic data with real camera trap images, resulting in a considerable decrease in classification error rates compared to using unaligned synthetic data.
The natural world is long-tailed: rare classes are observed orders of magnitudes less frequently than common ones, leading to highly-imbalanced data where rare classes can have only handfuls of examples. Learning from few examples is a known challenge for deep learning based classification algorithms, and is the focus of the field of low-shot learning. One potential approach to increase the training data for these rare classes is to augment the limited real data with synthetic samples. This has been shown to help, but the domain shift between real and synthetic hinders the approaches' efficacy when tested on real data. We explore the use of image-to-image translation methods to close the domain gap between synthetic and real imagery for animal species classification in data collected from camera traps: motion-activated static cameras used to monitor wildlife. We use low-level feature alignment between source and target domains to make synthetic data for a rare species generated using a graphics engine more "realistic". Compared against a system augmented with unaligned synthetic data, our experiments show a considerable decrease in classification error rates on a rare species.