Improving the performance of object detection by preserving label distribution

TL;DR

This paper introduces a method to address class imbalance in object detection datasets by maintaining uniform class distribution through multi-label stratification, improving detection performance on imbalanced and small datasets.

Contribution

The study proposes a novel multi-label stratification approach to balance class distribution in object detection training datasets, enhancing performance on imbalanced data.

Findings

Effective on datasets with severe class imbalance

Improves detection accuracy on small datasets

More beneficial than traditional methods on imbalanced data

Abstract

Object detection is a task that performs position identification and label classification of objects in images or videos. The information obtained through this process plays an essential role in various tasks in the field of computer vision. In object detection, the data utilized for training and validation typically originate from public datasets that are well-balanced in terms of the number of objects ascribed to each class in an image. However, in real-world scenarios, handling datasets with much greater class imbalance, i.e., very different numbers of objects for each class , is much more common, and this imbalance may reduce the performance of object detection when predicting unseen test images. In our study, thus, we propose a method that evenly distributes the classes in an image for training and validation, solving the class imbalance problem in object detection. Our proposed method aims to maintain a uniform class distribution through multi-label stratification. We tested our proposed method not only on public datasets that typically exhibit balanced class distribution but also on custom datasets that may have imbalanced class distribution. We found that our proposed method was more effective on datasets containing severe imbalance and less data. Our findings indicate that the proposed method can be effectively used on datasets with substantially imbalanced class distribution.