Adaptive neural networks for intelligent data-driven development

Youssef Shoeb

Abstract:

Advances in machine learning methods for computer vision tasks have led to their consideration for safetycritical 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.