MOCHA通过移动云协同提升视频分析模型对环境变化的响应速度。
Responsive DNN Adaptation for Video Analytics against Environment Shift via Hierarchical Mobile-Cloud Collaborations
- 移动端先复用旧模型并快速微调，再向云端请求更新
- 云端用语义分析构建模型索引，检索效率提升35.5倍
- 频繁场景预加载模型权重，适合实时视频分析应用
移动视频分析系统常面临部署环境变化，导致对已部署“专家DNN模型”自适应的响应性要求更高。现有框架多采用云中心模式，自适应过程中性能下降且对环境变化反应延迟。本文提出MOCHA框架，通过移动与云端的分层协作，优化持续模型自适应的响应性。具体包括：（1）通过设备端模型复用与快速微调，降低自适应响应延迟；（2）利用云端基础模型分析领域语义，构建结构化分类体系作为索引，加速历史专家模型检索；（3）通过维护本地专家模型缓存，对常见场景主动预取云端模型权重。在三个DNN任务的真实视频数据集上评估显示，MOCHA在自适应期间最高提升模型准确率6.8%，同时将响应延迟和重训练时间分别减少35.5倍和3.0倍。
原文摘要 · Abstract (English)
Mobile video analysis systems often encounter various deploying environments, where environment shifts present greater demands for responsiveness in adaptations of deployed "expert DNN models". Existing model adaptation frameworks primarily operate in a cloud-centric way, exhibiting degraded performance during adaptation and delayed reactions to environment shifts. Instead, this paper proposes MOCHA, a novel framework optimizing the responsiveness of continuous model adaptation through hierarchical collaborations between mobile and cloud resources. Specifically, MOCHA (1) reduces adaptation response delays by performing on-device model reuse and fast fine-tuning before requesting cloud model retrieval and end-to-end retraining; (2) accelerates history expert model retrieval by organizing them into a structured taxonomy utilizing domain semantics analyzed by a cloud foundation model as indices; (3) enables efficient local model reuse by maintaining onboard expert model caches for frequent scenes, which proactively prefetch model weights from the cloud model database. Extensive evaluations with real-world videos on three DNN tasks show MOCHA improves the model accuracy during adaptation by up to 6.8% while saving the response delay and retraining time by up to 35.5x and 3.0x respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。