# Learned Disentangled Latent Representations for Scalable Image Coding for Humans and Machines

arXiv: https://arxiv.org/abs/2301.04183 · HTML: https://mlsanity.com/paper/2301.04183/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jan 2023.

## Built on by (most cited first, 4 of 4)

- [Task-Aware Encoder Control for Deep Video Compression](https://mlsanity.com/paper/2404.04848/) (2024)
- [VVC+M: Plug and Play Scalable Image Coding for Humans and Machines](https://mlsanity.com/paper/2305.10453/) (2023)
- [Conditional and Residual Methods in Scalable Coding for Humans and Machines](https://mlsanity.com/paper/2305.02562/) (2023)
- [CI-ICM: Channel Importance-driven Learned Image Coding for Machines](https://mlsanity.com/paper/2604.05347/) (2026)

## Abstract (arXiv)

As an increasing amount of image and video content will be analyzed by machines, there is demand for a new codec paradigm that is capable of compressing visual input primarily for the purpose of computer vision inference, while secondarily supporting input reconstruction. In this work, we propose a learned compression architecture that can be used to build such a codec. We introduce a novel variational formulation that explicitly takes feature data relevant to the desired inference task as input at the encoder side. As such, our learned scalable image codec encodes and transmits two disentangled latent representations for object detection and input reconstruction. We note that compared to relevant benchmarks, our proposed scheme yields a more compact latent representation that is specialized for the inference task. Our experiments show that our proposed system achieves a bit rate savings of 40.6% on the primary object detection task compared to the current state-of-the-art, albeit with some degradation in performance for the secondary input reconstruction task.