Bridging the Gap: Simultaneous Fine Tuning for Data Re-Balancing
This addresses data imbalance issues in classification tasks, particularly for domains like sonar imaging, but appears incremental as it builds on existing limited data methods.
The paper tackles the problem of data imbalance in classification by proposing a simultaneous fine-tuning strategy that uses supplemental images similar to the limited data class to aid neural network training, showing results on a real-world synthetic aperture sonar dataset.
There are many real-world classification problems wherein the issue of data imbalance (the case when a data set contains substantially more samples for one/many classes than the rest) is unavoidable. While under-sampling the problematic classes is a common solution, this is not a compelling option when the large data class is itself diverse and/or the limited data class is especially small. We suggest a strategy based on recent work concerning limited data problems which utilizes a supplemental set of images with similar properties to the limited data class to aid in the training of a neural network. We show results for our model against other typical methods on a real-world synthetic aperture sonar data set. Code can be found at github.com/JohnMcKay/dataImbalance.