Few-Shot Batch Incremental Road Object Detection via Detector Fusion
This work addresses the problem of detecting rare road objects with minimal data for autonomous driving systems, representing an incremental improvement in few-shot detection methods.
The paper tackles batch incremental few-shot road object detection by proposing DualFusion, a method that combines object detectors to learn rare objects with limited data while maintaining performance on abundant classes. It achieves state-of-the-art results, including a mAP50 score of 40.0 on base classes and 38.8 overall on the IDD dataset, and a novel AP score of 9.9 on COCO, surpassing previous methods by over 6.6 times.
Incremental few-shot learning has emerged as a new and challenging area in deep learning, whose objective is to train deep learning models using very few samples of new class data, and none of the old class data. In this work we tackle the problem of batch incremental few-shot road object detection using data from the India Driving Dataset (IDD). Our approach, DualFusion, combines object detectors in a manner that allows us to learn to detect rare objects with very limited data, all without severely degrading the performance of the detector on the abundant classes. In the IDD OpenSet incremental few-shot detection task, we achieve a mAP50 score of 40.0 on the base classes and an overall mAP50 score of 38.8, both of which are the highest to date. In the COCO batch incremental few-shot detection task, we achieve a novel AP score of 9.9, surpassing the state-of-the-art novel class performance on the same by over 6.6 times.