# Near-Lossless Deep Feature Compression for Collaborative Intelligence

arXiv: https://arxiv.org/abs/1804.09963 · HTML: https://mlsanity.com/paper/1804.09963/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2018.

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

- [Collaborative Intelligence: Challenges and Opportunities](https://mlsanity.com/paper/2102.06841/) (2021)
- [Lightweight compression of neural network feature tensors for collaborative intelligence](https://mlsanity.com/paper/2105.06002/) (2021)
- [A Coding Framework and Benchmark towards Low-Bitrate Video Understanding](https://mlsanity.com/paper/2202.02813/) (2022)
- [SMC++: Masked Learning of Unsupervised Video Semantic Compression](https://mlsanity.com/paper/2406.04765/) (2024)
- [Scalable Video Coding for Humans and Machines](https://mlsanity.com/paper/2208.02512/) (2022)
- [Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence](https://mlsanity.com/paper/2105.07102/) (2021)
- [Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation](https://mlsanity.com/paper/2105.00591/) (2021)
- [Rate-Distortion in Image Coding for Machines](https://mlsanity.com/paper/2209.11694/) (2022)
- [Deep Joint Source-Channel Coding for Multi-Task Network](https://mlsanity.com/paper/2109.05779/) (2021)
- [Learned Point Cloud Compression for Classification](https://mlsanity.com/paper/2308.05959/) (2023)
- [SpikeBottleNet: Spike-Driven Feature Compression Architecture for Edge-Cloud Co-Inference](https://mlsanity.com/paper/2410.08673/) (2024)
- [DeDelayed: Deleting Remote Inference Delay via On-Device Correction](https://mlsanity.com/paper/2510.13714/) (2025)
- [Texture-guided Coding for Deep Features](https://mlsanity.com/paper/2405.19669/) (2024)
- [Latent-Space Inpainting for Packet Loss Concealment in Collaborative Object Detection](https://mlsanity.com/paper/2102.00142/) (2021)
- [Analysis of Latent-Space Motion for Collaborative Intelligence](https://mlsanity.com/paper/2102.04018/) (2021)
- [DFTS2: Simulating Deep Feature Transmission Over Packet Loss Channels](https://mlsanity.com/paper/2112.00794/) (2021)
- [Bandwidth-adaptive Cloud-Assisted 360-Degree 3D Perception for Autonomous Vehicles](https://mlsanity.com/paper/2602.23871/) (2026)

## Abstract (arXiv)

Collaborative intelligence is a new paradigm for efficient deployment of deep neural networks across the mobile-cloud infrastructure. By dividing the network between the mobile and the cloud, it is possible to distribute the computational workload such that the overall energy and/or latency of the system is minimized. However, this necessitates sending deep feature data from the mobile to the cloud in order to perform inference. In this work, we examine the differences between the deep feature data and natural image data, and propose a simple and effective near-lossless deep feature compressor. The proposed method achieves up to 5% bit rate reduction compared to HEVC-Intra and even more against other popular image codecs. Finally, we suggest an approach for reconstructing the input image from compressed deep features in the cloud, that could serve to supplement the inference performed by the deep model.