Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing

Abstract

The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical. To better enable the intelligent sensing at the front-end, instead of compressing and transmitting visual signals or the ultimately utilized top-layer deep learning features, we propose to compactly represent and convey the intermediate-layer deep learning features of high generalization capability, to facilitate the collaborating approach between front and cloud ends. This strategy enables a good balance among the computational load, transmission load and the generalization ability for cloud servers when deploying the deep neural networks for large scale cloud based visual analysis. Moreover, the presented strategy also makes the standardization of deep feature coding more feasible and promising, as a series of tasks can simultaneously benefit from the transmitted intermediate layers. We also present the results for evaluation of lossless deep feature compression with four benchmark data compression methods, which provides meaningful investigations and baselines for future research and standardization activities.

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• YOLOv3: An Incremental Improvement
• End to End Learning for Self-Driving Cars
• FitNets: Hints for Thin Deep Nets
• Hierarchical Question-Image Co-Attention for Visual Question Answering
• Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
• DeepID3: Face Recognition with Very Deep Neural Networks
• Ternary Weight Networks
• Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
• Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval
• A Survey of FPGA-Based Neural Network Accelerator
• Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval
• Deep Image Retrieval: Learning global representations for image search
• Compact Descriptors for Video Analysis: the Emerging MPEG Standard
• AI Oriented Large-Scale Video Management for Smart City: Technologies, Standards and Beyond

Cited by in corpus (2)

• Embedded deep learning in ophthalmology: Making ophthalmic imaging smarter
• Towards Collaborative Intelligence Friendly Architectures for Deep Learning