Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence
In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a lightweight device such as a mobile phone or edge device, and the remaining portion of the DNN is processed where more computing resources are available, such as in the cloud. This paper presents a novel...
Main Authors: | Robert A. Cohen, Hyomin Choi, Ivan V. Bajic |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Open Journal of Circuits and Systems |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9430648/ |
Similar Items
-
BBNet: A Novel Convolutional Neural Network Structure in Edge-Cloud Collaborative Inference
by: Hongbo Zhou, et al.
Published: (2021-06-01) -
Auto-Tiler: Variable-Dimension Autoencoder with Tiling for Compressing Intermediate Feature Space of Deep Neural Networks for Internet of Things
by: Jeongsoo Park, et al.
Published: (2021-01-01) -
A Deep Learning Framework of Quantized Compressed Sensing for Wireless Neural Recording
by: Biao Sun, et al.
Published: (2016-01-01) -
Estimating Previous Quantization Factors on Multiple JPEG Compressed Images
by: Sebastiano Battiato, et al.
Published: (2021-06-01) -
IMAGE COMPRESSION USING SELF-ORGANIZING FEATURE MAP AND WAVELET TRANSFORMATION
by: G. Muthu Lakshmi, et al.
Published: (2012-08-01)