AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics
Preprint
Abstract
The rapid evolution of multimedia and computer vision technologies requires adaptive visual model deployment strategies to effectively handle diverse tasks and varying environments. This work introduces AxiomVision, a novel framework that can guarantee accuracy by leveraging edge computing to dynamically select the most efficient visual models for video analytics under diverse scenarios. Utilizing a tiered edge-cloud architecture, AxiomVision enables the deployment of a broad spectrum of visual models, from lightweight to complex DNNs, that can be tailored to specific scenarios while considering camera source impacts. In addition, AxiomVision provides three core innovations: (1) a dynamic visual model selection mechanism utilizing continual online learning, (2) an efficient online method that efficiently takes into account the influence of the camera's perspective, and (3) a topology-driven grouping approach that accelerates the model selection process. With rigorous theoretical guarantees, these advancements provide a scalable and effective solution for visual tasks inherent to multimedia systems, such as object detection, classification, and counting. Empirically, AxiomVision achieves a 25.7\% improvement in accuracy.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Conversational Recommendation With Online Learning and Clustering on Misspecified UsersIEEE Transactions on Knowledge and Data Engineering, 2024
- End-Edge Coordinated Joint Encoding and Neural Enhancement for Low-Light Video Analytics2023
- ILCAS: Imitation Learning-Based Configuration- Adaptive Streaming for Live Video Analytics With Cross-Camera CollaborationIEEE Transactions on Mobile Computing, 2023
- Learning-Based Query Scheduling and Resource Allocation for Low-Latency Mobile-Edge Video AnalyticsIEEE Internet of Things Journal, 2023
- EdgeAdaptor: Online Configuration Adaption, Model Selection and Resource Provisioning for Edge DNN Inference Serving at ScaleIEEE Transactions on Mobile Computing, 2022
- Low-Latency Edge Video Analytics for On-Road Perception of Autonomous Ground VehiclesIEEE Transactions on Industrial Informatics, 2022
- Sensitivity-Aware Spatial Quality Adaptation for Live Video AnalyticsIEEE Journal on Selected Areas in Communications, 2022
- RESPIRE: Reducing Spatial–Temporal Redundancy for Efficient Edge-Based Industrial Video AnalyticsIEEE Transactions on Industrial Informatics, 2022
- Edge Coordinated Query Configuration for Low-Latency and Accurate Video AnalyticsIEEE Transactions on Industrial Informatics, 2019
- LSTM and Edge Computing for Big Data Feature Recognition of Industrial Electrical EquipmentIEEE Transactions on Industrial Informatics, 2019