ApproxNet: Content and Contention-Aware Video Analytics System for Embedded Clients
arXiv:1909.02068
Abstract
Videos take a lot of time to transport over the network, hence running analytics on the live video on embedded or mobile devices has become an important system driver. Considering that such devices, e.g., surveillance cameras or AR/VR gadgets, are resource constrained, creating lightweight deep neural networks (DNNs) for embedded devices is crucial. None of the current approximation techniques for object classification DNNs can adapt to changing runtime conditions, e.g., changes in resource availability on the device, the content characteristics, or requirements from the user. In this paper, we introduce ApproxNet, a video object classification system for embedded or mobile clients. It enables novel dynamic approximation techniques to achieve desired inference latency and accuracy trade-off under changing runtime conditions. It achieves this by enabling two approximation knobs within a single DNN model, rather than creating and maintaining an ensemble of models (e.g., MCDNN [MobiSys-16]. We show that ApproxNet can adapt seamlessly at runtime to these changes, provides low and stable latency for the image and video frame classification problems, and show the improvement in accuracy and latency over ResNet [CVPR-16], MCDNN [MobiSys-16], MobileNets [Google-17], NestDNN [MobiCom-18], and MSDNet [ICLR-18].
arXiv commentThis paper has been accepted to appear in ACM Transactions on Sensor Networks in 2021
References in corpus (14)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Two-Stream Convolutional Networks for Action Recognition in Videos
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
- Compressing Neural Networks with the Hashing Trick
- Multi-Scale Dense Networks for Resource Efficient Image Classification
- Seq-NMS for Video Object Detection
- Focus: Querying Large Video Datasets with Low Latency and Low Cost
- Modeling the Resource Requirements of Convolutional Neural Networks on Mobile Devices
- Resolution Adaptive Networks for Efficient Inference