Multi-Stream Cellular Test-Time Adaptation of Real-Time Models Evolving in Dynamic Environments
- URL: http://arxiv.org/abs/2404.17930v1
- Date: Sat, 27 Apr 2024 15:00:57 GMT
- Title: Multi-Stream Cellular Test-Time Adaptation of Real-Time Models Evolving in Dynamic Environments
- Authors: Benoît Gérin, Anaïs Halin, Anthony Cioppa, Maxim Henry, Bernard Ghanem, Benoît Macq, Christophe De Vleeschouwer, Marc Van Droogenbroeck,
- Abstract summary: Smart objects, notably autonomous vehicles, face challenges in critical local computations due to limited resources.
We propose a novel Multi-Stream Cellular Test-Time Adaptation setup where models adapt on the fly to a dynamic environment divided into cells.
We validate our methodology in the context of autonomous vehicles navigating across cells defined based on location and weather conditions.
- Score: 53.79708667153109
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- Automatic AI Model Selection for Wireless Systems: Online Learning via Digital Twinning [50.332027356848094]
AI-based applications are deployed at intelligent controllers to carry out functionalities like scheduling or power control.
The mapping between context and AI model parameters is ideally done in a zero-shot fashion.
This paper introduces a general methodology for the online optimization of AMS mappings.
arXiv Detail & Related papers (2024-06-22T11:17:50Z) - Drive Anywhere: Generalizable End-to-end Autonomous Driving with
Multi-modal Foundation Models [114.69732301904419]
We present an approach to apply end-to-end open-set (any environment/scene) autonomous driving that is capable of providing driving decisions from representations queryable by image and text.
Our approach demonstrates unparalleled results in diverse tests while achieving significantly greater robustness in out-of-distribution situations.
arXiv Detail & Related papers (2023-10-26T17:56:35Z) - AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation [1.4530711901349282]
We propose to validate test-time adaptation methods using datasets for autonomous driving, namely CLAD-C and SHIFT.
We observe that current test-time adaptation methods struggle to effectively handle varying degrees of domain shift.
We enhance the well-established self-training framework by incorporating a small memory buffer to increase model stability.
arXiv Detail & Related papers (2023-09-18T19:34:23Z) - Single-Cell Multimodal Prediction via Transformers [36.525050229323845]
We propose scMoFormer to model the complex interactions among different modalities.
scMoFormer won a Kaggle silver medal with the rank of 24/1221 (Top 2%) without ensemble in a NeurIPS 2022 competition.
arXiv Detail & Related papers (2023-03-01T05:03:23Z) - Parallel Successive Learning for Dynamic Distributed Model Training over
Heterogeneous Wireless Networks [50.68446003616802]
Federated learning (FedL) has emerged as a popular technique for distributing model training over a set of wireless devices.
We develop parallel successive learning (PSL), which expands the FedL architecture along three dimensions.
Our analysis sheds light on the notion of cold vs. warmed up models, and model inertia in distributed machine learning.
arXiv Detail & Related papers (2022-02-07T05:11:01Z) - Learning to Continuously Optimize Wireless Resource in a Dynamic
Environment: A Bilevel Optimization Perspective [52.497514255040514]
This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment.
We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes.
Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
arXiv Detail & Related papers (2021-05-03T07:23:39Z) - Learning to Continuously Optimize Wireless Resource In Episodically
Dynamic Environment [55.91291559442884]
This work develops a methodology that enables data-driven methods to continuously learn and optimize in a dynamic environment.
We propose to build the notion of continual learning into the modeling process of learning wireless systems.
Our design is based on a novel min-max formulation which ensures certain fairness" across different data samples.
arXiv Detail & Related papers (2020-11-16T08:24:34Z) - LUNAR: Cellular Automata for Drifting Data Streams [19.98517714325424]
We propose LUNAR, a streamified version of cellular automata.
It is able to act as a real incremental learner while adapting to drifting conditions.
arXiv Detail & Related papers (2020-02-06T09:10:43Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.