# End-to-end Learning of Compressible Features

arXiv: https://arxiv.org/abs/2007.11797 · HTML: https://mlsanity.com/paper/2007.11797/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2020.

## Built on by (most cited first, 30 of 43)

- [Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models](https://mlsanity.com/paper/2301.11189/) (2023)
- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [Communication-Efficient Collaborative Perception via Information Filling with Codebook](https://mlsanity.com/paper/2405.04966/) (2024)
- [Lossy Compression for Lossless Prediction](https://mlsanity.com/paper/2106.10800/) (2021)
- [Supervised Compression for Resource-Constrained Edge Computing Systems](https://mlsanity.com/paper/2108.11898/) (2021)
- [Image Coding for Machines with Omnipotent Feature Learning](https://mlsanity.com/paper/2207.01932/) (2022)
- [A Coding Framework and Benchmark towards Low-Bitrate Video Understanding](https://mlsanity.com/paper/2202.02813/) (2022)
- [SC2 Benchmark: Supervised Compression for Split Computing](https://mlsanity.com/paper/2203.08875/) (2022)
- [Learned Image Compression for Machine Perception](https://mlsanity.com/paper/2111.02249/) (2021)
- [FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing](https://mlsanity.com/paper/2302.10681/) (2023)
- [Semantically Structured Image Compression via Irregular Group-Based Decoupling](https://mlsanity.com/paper/2305.02586/) (2023)
- [SMC++: Masked Learning of Unsupervised Video Semantic Compression](https://mlsanity.com/paper/2406.04765/) (2024)
- [Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics](https://mlsanity.com/paper/2110.09241/) (2021)
- [Rate-Distortion-Cognition Controllable Versatile Neural Image Compression](https://mlsanity.com/paper/2407.11700/) (2024)
- [Pragmatic Communication in Multi-Agent Collaborative Perception](https://mlsanity.com/paper/2401.12694/) (2024)
- [Lossy Neural Compression for Geospatial Analytics: A Review](https://mlsanity.com/paper/2503.01505/) (2025)
- [End-to-end optimized image compression for multiple machine tasks](https://mlsanity.com/paper/2103.04178/) (2021)
- [C3-SL: Circular Convolution-Based Batch-Wise Compression for Communication-Efficient Split Learning](https://mlsanity.com/paper/2207.12397/) (2022)
- [Feature Compression for Rate Constrained Object Detection on the Edge](https://mlsanity.com/paper/2204.07314/) (2022)
- [Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts](https://mlsanity.com/paper/2305.02578/) (2023)
- [DMOFC: Discrimination Metric-Optimized Feature Compression](https://mlsanity.com/paper/2405.04044/) (2024)
- [NeuCo-Bench: A Novel Benchmark Framework for Neural Embeddings in Earth Observation](https://mlsanity.com/paper/2510.17914/) (2025)
- [FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression](https://mlsanity.com/paper/2403.16677/) (2024)
- [A Multi-task Supervised Compression Model for Split Computing](https://mlsanity.com/paper/2501.01420/) (2025)
- [Distributed Semantic Segmentation with Efficient Joint Source and Task Decoding](https://mlsanity.com/paper/2407.11224/) (2024)
- [Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior](https://mlsanity.com/paper/2511.22549/) (2025)
- [Progressive Neural Compression for Adaptive Image Offloading under Timing Constraints](https://mlsanity.com/paper/2310.05306/) (2023)
- [Compressed Feature Quality Assessment: Dataset and Baselines](https://mlsanity.com/paper/2506.07412/) (2025)
- [Recognition-Aware Learned Image Compression](https://mlsanity.com/paper/2202.00198/) (2022)
- [Adversarial Attacks to Latent Representations of Distributed Neural Networks in Split Computing](https://mlsanity.com/paper/2309.17401/) (2023)

## Abstract (arXiv)

Pre-trained convolutional neural networks (CNNs) are powerful off-the-shelf feature generators and have been shown to perform very well on a variety of tasks. Unfortunately, the generated features are high dimensional and expensive to store: potentially hundreds of thousands of floats per example when processing videos. Traditional entropy based lossless compression methods are of little help as they do not yield desired level of compression, while general purpose lossy compression methods based on energy compaction (e.g. PCA followed by quantization and entropy coding) are sub-optimal, as they are not tuned to task specific objective. We propose a learned method that jointly optimizes for compressibility along with the task objective for learning the features. The plug-in nature of our method makes it straight-forward to integrate with any target objective and trade-off against compressibility. We present results on multiple benchmarks and demonstrate that our method produces features that are an order of magnitude more compressible, while having a regularization effect that leads to a consistent improvement in accuracy.