Analysis of Latent-Space Motion for Collaborative Intelligence
Not on the map. Why?
Abstract (arXiv)
When the input to a deep neural network (DNN) is a video signal, a sequence of feature tensors is produced at the intermediate layers of the model. If neighboring frames of the input video are related through motion, a natural question is, "what is the relationship between the corresponding feature tensors?" By analyzing the effect of common DNN operations on optical flow, we show that the motion present in each channel of a feature tensor is approximately equal to the scaled version of the input motion. The analysis is validated through experiments utilizing common motion models. %These results will be useful in collaborative intelligence applications where sequences of feature tensors need to be compressed or further analyzed.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 22 references that are in the map. First posted on arXiv 8 Feb 2021.
Builds on
12 of 22 references.
References · 12
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2020Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analyticscited by 80
- 2018JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Servicescited by 79
- 2018Deep feature compression for collaborative object detectioncited by 48
- 2019Multi-task learning with compressible features for Collaborative Intelligencecited by 20
- 2018Near-Lossless Deep Feature Compression for Collaborative Intelligencecited by 17
- 2020Pareto-Optimal Bit Allocation for Collaborative Intelligencecited by 17
- 2020Back-and-Forth prediction for deep tensor compressioncited by 16
- 2018Deep Frame Prediction for Video Codingcited by 13
- 2020Bit Allocation for Multi-Task Collaborative Intelligencecited by 13
- 2020Shared Mobile-Cloud Inference for Collaborative Intelligencecited by 1
Built on by
Not cited yet.