OpenNet: Incremental Learning for Autonomous Driving Object Detection with Balanced Loss
This work addresses incremental learning challenges for autonomous driving systems, but it is incremental as it builds on existing techniques like balanced loss and feature distillation.
The paper tackles the problem of class imbalance and catastrophic forgetting in autonomous driving object detection by proposing OpenNet with Balanced Loss and incremental learning techniques, achieving better performance on the CODA dataset compared to existing methods.
Automated driving object detection has always been a challenging task in computer vision due to environmental uncertainties. These uncertainties include significant differences in object sizes and encountering the class unseen. It may result in poor performance when traditional object detection models are directly applied to automated driving detection. Because they usually presume fixed categories of common traffic participants, such as pedestrians and cars. Worsely, the huge class imbalance between common and novel classes further exacerbates performance degradation. To address the issues stated, we propose OpenNet to moderate the class imbalance with the Balanced Loss, which is based on Cross Entropy Loss. Besides, we adopt an inductive layer based on gradient reshaping to fast learn new classes with limited samples during incremental learning. To against catastrophic forgetting, we employ normalized feature distillation. By the way, we improve multi-scale detection robustness and unknown class recognition through FPN and energy-based detection, respectively. The Experimental results upon the CODA dataset show that the proposed method can obtain better performance than that of the existing methods.