Continual Learning Strategy in One-Stage Object Detection Framework Based on Experience Replay for Autonomous Driving Vehicle

Abstract

Object detection is an important aspect for autonomous driving vehicles (ADV), which may comprise of a machine learning model that detects a range of classes. As the deployment of ADV widens globally, the variety of objects to be detected may increase beyond the designated range of classes. Continual learning for object detection essentially ensure a robust adaptation of a model to detect additional classes on the fly. This study proposes a novel continual learning method for object detection that learns new object class(es) along with cumulative memory of classes from prior learning rounds to avoid any catastrophic forgetting. The results of PASCAL VOC 2007 have suggested that the proposed ER method obtains 4.3% of mAP drop compared against the all-classes learning, which is the lowest amongst other prior arts.

Scale-Invariant Multidirectional License Plate Detection with the Network Combining Indirect and Direct Branches

“…Moreover, the ALPD module, the indirect detection branch, and the whole detection network have almost the same vehicle detection performance as the vanilla SSD [ 36 ]. This way, it proves our method can continuously improve the license plate detection performance while maintaining the vehicle detection performance [ 43 , 44 , 45 , 46 , 47 ].…”

Continual Object Detection: A review of definitions, strategies, and challenges

“…Shin et al [35] proposed to train a generative model on the old data distribution and use it to generate fake samples that help in mitigating the forgetting of old classes. Although having the downside of the model's performance being upper-bounded by the joint-training in all tasks [20], the replay family has been the most consistently used strategy in real-world applications of CL [6,36].…”

“…Hao et al [82] employed the use of a small buffer of samples along with logits distillation to perform better than its competitors in the incremental learning of common objects from vending machines. Shieh et al [36] proposed the use of experience replay with different buffer sizes and the YOLO-V3 architecture for the problem of adding multiple classes at once to an object detector. They evaluated their approach in a common benchmark and on a private autonomous driving dataset.…”

An incremental object detection model based on knowledge distillation

“…However, there are often situations where the requirements change, leading to a continuous increase in the types of objects to be recognized, which exceeds the recognition capabilities of the original model. In such cases, training the model with the new types of objects can cause the model to lose its ability to recognize the old object, which is known as catastrophic forgetting 2 . On the other hand, training the model from scratch using a dataset containing both new and old object types 3 can achieve good recognition performance but suffers from low efficiency and lacks real-time learning capability for new object classifications 4 .…”