Detection of Autonomous Shuttles in Urban Traffic Images Using Adaptive Residual Context

2026-03-16

AI Summary

This work addresses the challenge of incrementally detecting novel autonomous shuttle vehicles in urban traffic imagery, where conventional fine-tuning approaches often suffer from catastrophic forgetting, degrading performance on previously learned traffic scenes. To mitigate this issue, the authors propose an Adaptive Residual Context (ARC) architecture that freezes the pre-trained backbone network while introducing a trainable task-specific branch alongside a frozen context branch. Spatial features are effectively transferred through a context-guided bridge augmented with an attention mechanism. Without updating the backbone parameters, ARC efficiently acquires knowledge of new classes while preserving prior understanding. Experimental results on a newly curated dataset demonstrate that ARC achieves detection performance comparable to full fine-tuning while substantially improving knowledge retention, offering a data-efficient solution for incremental object detection in urban environments.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• autonomous shuttles
• video object detection
• catastrophic forgetting
• scene understanding
• urban traffic

Innovation

• Adaptive Residual Context
• catastrophic forgetting
• context preservation
• video object detection
• attention mechanism