Multi-Stream Cellular Test-Time Adaptation of Real-Time Models Evolving in Dynamic Environments
This work addresses real-time model adaptation challenges for smart objects like autonomous vehicles in IoT and 5G networks, though it appears incremental as it builds on existing test-time adaptation and student-teacher methods.
The paper tackles the problem of lightweight AI models struggling with diverse data distributions in dynamic IoT environments, such as autonomous vehicles, by proposing a Multi-Stream Cellular Test-Time Adaptation (MSC-TTA) setup and a real-time adaptive student-teacher method, showing that the multi-stream approach outperforms a single-stream baseline.
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.