# Turbo: Opportunistic Enhancement for Edge Video Analytics

arXiv: https://arxiv.org/abs/2207.00172 · HTML: https://mlsanity.com/paper/2207.00172/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 65 references that are in the map.
- First posted on arXiv 29 Jun 2022.

## Builds on (most cited first, 29 of 29)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation](https://mlsanity.com/paper/2003.13659/) (2020)
- [Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning](https://mlsanity.com/paper/1904.05050/) (2019)
- [CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification](https://mlsanity.com/paper/1903.09254/) (2019)
- [UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking](https://mlsanity.com/paper/1511.04136/) (2015)
- [NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision](https://mlsanity.com/paper/1810.10090/) (2018)
- [Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers](https://mlsanity.com/paper/2012.10557/) (2020)
- [PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report](https://mlsanity.com/paper/1810.01641/) (2018)
- [NoScope: Optimizing Neural Network Queries over Video at Scale](https://mlsanity.com/paper/1703.02529/) (2017)
- [From GAN to WGAN](https://mlsanity.com/paper/1904.08994/) (2019)
- [GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge](https://mlsanity.com/paper/2201.07705/) (2022)
- [Learning Invariant Representation for Unsupervised Image Restoration](https://mlsanity.com/paper/2003.12769/) (2020)
- [MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors](https://mlsanity.com/paper/1908.07985/) (2019)
- [Fast Video Classification via Adaptive Cascading of Deep Models](https://mlsanity.com/paper/1611.06453/) (2016)
- [Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems](https://mlsanity.com/paper/2104.09286/) (2021)

## Built on by (most cited first, 7 of 7)

- [Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniques](https://mlsanity.com/paper/2211.15751/) (2022)
- [AVA: Towards Agentic Video Analytics with Vision Language Models](https://mlsanity.com/paper/2505.00254/) (2025)
- [Dynamic Test-Time Augmentation via Differentiable Functions](https://mlsanity.com/paper/2212.04681/) (2022)
- [A Survey on Video Analytics in Cloud-Edge-Terminal Collaborative Systems](https://mlsanity.com/paper/2502.06581/) (2025)
- [Arena: A Patch-of-Interest ViT Inference Acceleration System for Edge-Assisted Video Analytics](https://mlsanity.com/paper/2404.09245/) (2024)
- [Legilimens: Performant Video Analytics on the System-on-Chip Edge](https://mlsanity.com/paper/2504.21136/) (2025)
- [Optimizing video analytics inference pipelines: a case study](https://mlsanity.com/paper/2512.07009/) (2025)

## Abstract (arXiv)

Edge computing is being widely used for video analytics. To alleviate the inherent tension between accuracy and cost, various video analytics pipelines have been proposed to optimize the usage of GPU on edge nodes. Nonetheless, we find that GPU compute resources provisioned for edge nodes are commonly under-utilized due to video content variations, subsampling and filtering at different places of a pipeline. As opposed to model and pipeline optimization, in this work, we study the problem of opportunistic data enhancement using the non-deterministic and fragmented idle GPU resources. In specific, we propose a task-specific discrimination and enhancement module and a model-aware adversarial training mechanism, providing a way to identify and transform low-quality images that are specific to a video pipeline in an accurate and efficient manner. A multi-exit model structure and a resource-aware scheduler is further developed to make online enhancement decisions and fine-grained inference execution under latency and GPU resource constraints. Experiments across multiple video analytics pipelines and datasets reveal that by judiciously allocating a small amount of idle resources on frames that tend to yield greater marginal benefits from enhancement, our system boosts DNN object detection accuracy by 7.3-11.3% without incurring any latency costs.