Split Computing for Complex Object Detectors: Challenges and Preliminary Results

Abstract

Following the trends of mobile and edge computing for DNN models, an intermediate option, split computing, has been attracting attentions from the research community. Previous studies empirically showed that while mobile and edge computing often would be the best options in terms of total inference time, there are some scenarios where split computing methods can achieve shorter inference time. All the proposed split computing approaches, however, focus on image classification tasks, and most are assessed with small datasets that are far from the practical scenarios. In this paper, we discuss the challenges in developing split computing methods for powerful R-CNN object detectors trained on a large dataset, COCO 2017. We extensively analyze the object detectors in terms of layer-wise tensor size and model size, and show that naive split computing methods would not reduce inference time. To the best of our knowledge, this is the first study to inject small bottlenecks to such object detectors and unveil the potential of a split computing approach. The source code and trained models' weights used in this study are available at https://github.com/yoshitomo-matsubara/hnd-ghnd-object-detectors .

Accepted to EMDL '20 (4th International Workshop on Embedded and Mobile Deep Learning) co-located with ACM MobiCom 2020

References in corpus (5)

• Distilling the Knowledge in a Neural Network
• Mobile Edge Computing: A Survey on Architecture and Computation Offloading
• Distributed Deep Neural Networks over the Cloud, the Edge and End Devices
• Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
• Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge

Cited by in corpus (5)

• Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
• Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
• BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing
• Neuromorphic Wireless Split Computing with Multi-Level Spikes
• Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation