A novel three-stage training strategy for long-tailed classification

TL;DR

This paper introduces a three-stage training strategy tailored for long-tailed SAR image classification, effectively addressing class imbalance and low-quality image challenges, resulting in improved accuracy.

Contribution

The paper proposes a novel three-stage training approach specifically designed for long-tailed SAR image datasets, enhancing classification performance.

Findings

Achieved top-1 accuracy of 22.34% in development phase.

Effectively handled class imbalance in SAR datasets.

Demonstrated superior results over existing methods.

Abstract

The long-tailed distribution datasets poses great challenges for deep learning based classification models on how to handle the class imbalance problem. Existing solutions usually involve class-balacing strategies or transfer learing from head- to tail-classes or use two-stages learning strategy to re-train the classifier. However, the existing methods are difficult to solve the low quality problem when images are obtained by SAR. To address this problem, we establish a novel three-stages training strategy, which has excellent results for processing SAR image datasets with long-tailed distribution. Specifically, we divide training procedure into three stages. The first stage is to use all kinds of images for rough-training, so as to get the rough-training model with rich content. The second stage is to make the rough model learn the feature expression by using the residual dataset with the class 0 removed. The third stage is to fine tune the model using class-balanced datasets with all 10 classes (including the overall model fine tuning and classifier re-optimization). Through this new training strategy, we only use the information of SAR image dataset and the network model with very small parameters to achieve the top 1 accuracy of 22.34 in development phase.