Multi-Stream Cellular Test-Time Adaptation of Real-Time Models Evolving in Dynamic Environments

TL;DR

This paper introduces MSC-TTA, a real-time multi-stream adaptation method for lightweight models in dynamic environments like autonomous vehicles, improving performance across changing data distributions.

Contribution

The paper proposes a novel multi-stream test-time adaptation framework and a real-time student-teacher method, along with a new synthetic dataset for benchmarking.

Findings

Multi-stream approach outperforms single-stream baseline.

Validated on autonomous vehicle navigation scenarios.

Released DADE dataset for future research.

Abstract

In the era of the Internet of Things (IoT), objects connect through a dynamic network, empowered by technologies like 5G, enabling real-time data sharing. However, smart objects, notably autonomous vehicles, face challenges in critical local computations due to limited resources. Lightweight AI models offer a solution but struggle with diverse data distributions. To address this limitation, we propose a novel Multi-Stream Cellular Test-Time Adaptation (MSC-TTA) setup where models adapt on the fly to a dynamic environment divided into cells. Then, we propose a real-time adaptive student-teacher method that leverages the multiple streams available in each cell to quickly adapt to changing data distributions. We validate our methodology in the context of autonomous vehicles navigating across cells defined based on location and weather conditions. To facilitate future benchmarking, we release a new multi-stream large-scale synthetic semantic segmentation dataset, called DADE, and show that our multi-stream approach outperforms a single-stream baseline. We believe that our work will open research opportunities in the IoT and 5G eras, offering solutions for real-time model adaptation.