Detection of Autonomous Shuttles in Urban Traffic Images Using Adaptive Residual Context
This addresses the need for safe and efficient monitoring of autonomous vehicles in urban traffic, though it is an incremental improvement over existing fine-tuning methods.
The paper tackled the problem of catastrophic forgetting when fine-tuning object detection models for new vehicle categories like autonomous shuttles in urban traffic, and the result was that the Adaptive Residual Context (ARC) architecture matched fine-tuned baselines while significantly improving knowledge retention.
The progressive automation of transport promises to enhance safety and sustainability through shared mobility. Like other vehicles and road users, and even more so for such a new technology, it requires monitoring to understand how it interacts in traffic and to evaluate its safety. This can be done with fixed cameras and video object detection. However, the addition of new detection targets generally requires a fine-tuning approach for regular detection methods. Unfortunately, this implementation strategy will lead to a phenomenon known as catastrophic forgetting, which causes a degradation in scene understanding. In road safety applications, preserving contextual scene knowledge is of the utmost importance for protecting road users. We introduce the Adaptive Residual Context (ARC) architecture to address this. ARC links a frozen context branch and trainable task-specific branches through a Context-Guided Bridge, utilizing attention to transfer spatial features while preserving pre-trained representations. Experiments on a custom dataset show that ARC matches fine-tuned baselines while significantly improving knowledge retention, offering a data-efficient solution to add new vehicle categories for complex urban environments.