# Responsive DNN Adaptation for Video Analytics against Environment Shift via Hierarchical Mobile-Cloud Collaborations

arXiv: https://arxiv.org/abs/2505.00745 · HTML: https://mlsanity.com/paper/2505.00745/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 89 references that are in the map.
- First posted on arXiv 30 Apr 2025.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [Expert Gate: Lifelong Learning with a Network of Experts](https://mlsanity.com/paper/1611.06194/) (2016)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models](https://mlsanity.com/paper/1911.03393/) (2019)
- [PowerInfer-2: Fast Large Language Model Inference on a Smartphone](https://mlsanity.com/paper/2406.06282/) (2024)
- [Learning to Continually Learn](https://mlsanity.com/paper/2002.09571/) (2020)
- [Model Compression with Adversarial Robustness: A Unified Optimization Framework](https://mlsanity.com/paper/1902.03538/) (2019)
- [Online Model Distillation for Efficient Video Inference](https://mlsanity.com/paper/1812.02699/) (2018)
- [DeepCache: Principled Cache for Mobile Deep Vision](https://mlsanity.com/paper/1712.01670/) (2017)
- [Online Continual Learning for Embedded Devices](https://mlsanity.com/paper/2203.10681/) (2022)
- [Focus: Querying Large Video Datasets with Low Latency and Low Cost](https://mlsanity.com/paper/1801.03493/) (2018)
- [BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics](https://mlsanity.com/paper/1805.01046/) (2018)
- [GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge](https://mlsanity.com/paper/2201.07705/) (2022)
- [Real-Time Video Inference on Edge Devices via Adaptive Model Streaming](https://mlsanity.com/paper/2006.06628/) (2020)
- [Fast Video Classification via Adaptive Cascading of Deep Models](https://mlsanity.com/paper/1611.06453/) (2016)
- [Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications](https://mlsanity.com/paper/2110.13290/) (2021)
- [Cost-effective On-device Continual Learning over Memory Hierarchy with Miro](https://mlsanity.com/paper/2308.06053/) (2023)
- [Scaling Video Analytics Systems to Large Camera Deployments](https://mlsanity.com/paper/1809.02318/) (2018)
- [THIA: Accelerating Video Analytics using Early Inference and Fine-Grained Query Planning](https://mlsanity.com/paper/2102.08481/) (2021)
- [Gemino: Practical and Robust Neural Compression for Video Conferencing](https://mlsanity.com/paper/2209.10507/) (2022)
- [Miriam: Exploiting Elastic Kernels for Real-time Multi-DNN Inference on Edge GPU](https://mlsanity.com/paper/2307.04339/) (2023)
- [On the Efficiency and Robustness of Vibration-based Foundation Models for IoT Sensing: A Case Study](https://mlsanity.com/paper/2404.02461/) (2024)
- [Soar: Design and Deployment of A Smart Roadside Infrastructure System for Autonomous Driving](https://mlsanity.com/paper/2404.13786/) (2024)

## Abstract (arXiv)

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.