Adaptive Neural Networks for Intelligent Data-Driven Development

TL;DR

This paper presents an adaptive neural network framework that enables continuous learning and integration of new classes in perception systems for autonomous driving, addressing challenges of dynamic environments and unknown object recognition.

Contribution

It introduces a scalable extension strategy, a no-retraining OoD detection component, and a retrieval-based data augmentation pipeline for adaptive perception systems.

Findings

Effective integration of new classes without performance loss

No retraining needed for new object detection

Enhanced safety in autonomous driving environments

Abstract

Advances in machine learning methods for computer vision tasks have led to their consideration for safety-critical applications like autonomous driving. However, effectively integrating these methods into the automotive development lifecycle remains challenging. Since the performance of machine learning algorithms relies heavily on the training data provided, the data and model development lifecycle play a key role in successfully integrating these components into the product development lifecycle. Existing models frequently encounter difficulties recognizing or adapting to novel instances not present in the original training dataset. This poses a significant risk for reliable deployment in dynamic environments. To address this challenge, we propose an adaptive neural network architecture and an iterative development framework that enables users to efficiently incorporate previously unknown objects into the current perception system. Our approach builds on continuous learning, emphasizing the necessity of dynamic updates to reflect real-world deployment conditions. Specifically, we introduce a pipeline with three key components: (1) a scalable network extension strategy to integrate new classes while preserving existing performance, (2) a dynamic OoD detection component that requires no additional retraining for newly added classes, and (3) a retrieval-based data augmentation process tailored for safety-critical deployments. The integration of these components establishes a pragmatic and adaptive pipeline for the continuous evolution of perception systems in the context of autonomous driving.