Influence-Balanced Loss for Imbalanced Visual Classification
This addresses class-imbalance problems in visual classification, offering a flexible solution that can be combined with various existing methods, though it appears incremental as it builds on prior imbalance learning techniques.
The paper tackles imbalanced visual classification by proposing a balancing training method with a new loss that reduces the influence of samples causing overfitted decision boundaries, demonstrating improved performance over state-of-the-art cost-sensitive loss methods on multiple benchmark datasets.
In this paper, we propose a balancing training method to address problems in imbalanced data learning. To this end, we derive a new loss used in the balancing training phase that alleviates the influence of samples that cause an overfitted decision boundary. The proposed loss efficiently improves the performance of any type of imbalance learning methods. In experiments on multiple benchmark data sets, we demonstrate the validity of our method and reveal that the proposed loss outperforms the state-of-the-art cost-sensitive loss methods. Furthermore, since our loss is not restricted to a specific task, model, or training method, it can be easily used in combination with other recent re-sampling, meta-learning, and cost-sensitive learning methods for class-imbalance problems.