# Lightweight compression of neural network feature tensors for collaborative intelligence

arXiv: https://arxiv.org/abs/2105.06002 · HTML: https://mlsanity.com/paper/2105.06002/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 12 May 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [Improving Neural Network Quantization without Retraining using Outlier Channel Splitting](https://mlsanity.com/paper/1901.09504/) (2019)
- [Scalable Methods for 8-bit Training of Neural Networks](https://mlsanity.com/paper/1805.11046/) (2018)
- [BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services](https://mlsanity.com/paper/1902.01000/) (2019)
- [WRPN: Wide Reduced-Precision Networks](https://mlsanity.com/paper/1709.01134/) (2017)
- [Deep feature compression for collaborative object detection](https://mlsanity.com/paper/1802.03931/) (2018)
- [Post-training 4-bit quantization of convolution networks for rapid-deployment](https://mlsanity.com/paper/1810.05723/) (2018)
- [Near-Lossless Deep Feature Compression for Collaborative Intelligence](https://mlsanity.com/paper/1804.09963/) (2018)
- [Back-and-Forth prediction for deep tensor compression](https://mlsanity.com/paper/2002.07036/) (2020)
- [Towards Collaborative Intelligence Friendly Architectures for Deep Learning](https://mlsanity.com/paper/1902.00147/) (2019)

## Built on by (most cited first, 17 of 17)

- [SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems](https://mlsanity.com/paper/2204.04705/) (2022)
- [Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence](https://mlsanity.com/paper/2105.07102/) (2021)
- [I-SPLIT: Deep Network Interpretability for Split Computing](https://mlsanity.com/paper/2209.11607/) (2022)
- [CALTeC: Content-Adaptive Linear Tensor Completion for Collaborative Intelligence](https://mlsanity.com/paper/2106.05531/) (2021)
- [Slimmable Encoders for Flexible Split DNNs in Bandwidth and Resource Constrained IoT Systems](https://mlsanity.com/paper/2306.12691/) (2023)
- [On the Impact of Black-box Deployment Strategies for Edge AI on Latency and Model Performance](https://mlsanity.com/paper/2403.17154/) (2024)
- [Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing](https://mlsanity.com/paper/2511.04002/) (2025)
- [Revisit Visual Representation in Analytics Taxonomy: A Compression Perspective](https://mlsanity.com/paper/2106.08512/) (2021)
- [AutoEncoder-Compressed Parallel Split Learning for Pre-trained Model Fine-Tuning](https://mlsanity.com/paper/2607.17913/) (2026)
- [DFTS2: Simulating Deep Feature Transmission Over Packet Loss Channels](https://mlsanity.com/paper/2112.00794/) (2021)
- [MetaMorphosis: Task-oriented Privacy Cognizant Feature Generation for Multi-task Learning](https://mlsanity.com/paper/2305.07815/) (2023)
- [Efficient IoT Inference via Context-Awareness](https://mlsanity.com/paper/2310.19112/) (2023)
- [Inter-Feature-Map Differential Coding of Surveillance Video](https://mlsanity.com/paper/2411.00984/) (2024)
- [Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Models](https://mlsanity.com/paper/2411.05961/) (2024)
- [Range Asymmetric Numeral Systems-Based Lightweight Intermediate Feature Compression for Split Computing of Deep Neural Networks](https://mlsanity.com/paper/2511.11664/) (2025)
- [Bandwidth-adaptive Cloud-Assisted 360-Degree 3D Perception for Autonomous Vehicles](https://mlsanity.com/paper/2602.23871/) (2026)
- [Trainable Bitwise Soft Quantization for Input Feature Compression](https://mlsanity.com/paper/2603.05172/) (2026)

## Abstract (arXiv)

In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a relatively low-complexity device such as a mobile phone or edge device, and the remainder of the DNN is processed where more computing resources are available, such as in the cloud. This paper presents a novel lightweight compression technique designed specifically to code the activations of a split DNN layer, while having a low complexity suitable for edge devices and not requiring any retraining. We also present a modified entropy-constrained quantizer design algorithm optimized for clipped activations. When applied to popular object-detection and classification DNNs, we were able to compress the 32-bit floating point activations down to 0.6 to 0.8 bits, while keeping the loss in accuracy to less than 1%. When compared to HEVC, we found that the lightweight codec consistently provided better inference accuracy, by up to 1.3%. The performance and simplicity of this lightweight compression technique makes it an attractive option for coding a layer's activations in split neural networks for edge/cloud applications.