[3S6-GS-2] Machine learning:

[3S6-GS-2-02] Adaptive Learning Method to Achieve Both High Accuracy and Improved Recall for Critical Classes

〇Kazuki Iijima¹, Takashi Washio² (1. Osaka University, 2. Kansai University)

Keywords:Deep Learning-based Image Classification, Improvement of Recall, Adaptive Learning

Deep learning-based image classification models are widely utilized in various fields such as anomaly detection, object recognition, and medical image analysis. In these application domains, classification models and learning algorithms typically aim to maximize overall classification accuracy by treating all classes equally. However, in real-world scenarios, there is often a demand for enhancing the recall of specific critical classes while maintaining overall classification accuracy, as seen in the detection of specific diseases in medical diagnostic systems or pedestrian recognition in autonomous driving systems. Such adjustments, however, often involve a trade-off, where improvements in the recall of critical classes lead to a decline in overall model accuracy. To address this challenge, this study proposes a novel learning method that enhances the recall of critical classes while preserving overall accuracy. The method incorporates a weighting mechanism into the widely used cross-entropy loss function, dynamically adjusting the importance of classes based on the output probabilities generated during the training process. This adaptive approach aims to improve the recall of critical classes without compromising the overall performance of the model.