Effect of Stage Training for Long-Tailed Multi-Label Image Classification

Abstract

In this study, we focus on the multi-stage training approach for training image classification models in the ICCV CVAMD 2023 Shared Task CXR-LT: Multi-Label LongTailed Classification on Chest X-Rays. In the proposed approach, the input image size and batch size are adjusted at each stage of the training process. In the first stage, we use a smaller input image size and a larger batch size for model training. Following that, we increase the image size and reduce the batch size in the second stage. A thorough search of the related literature did not yield validations of a similar approach for data with a long-tailed distribution. We successfully balance accelerated model training and performance by combining the proposed technique with various enhancements, such as oversampling, postprocessing using view positions, and ensemble methods, despite using a smaller model architecture and smaller input image size.