# Latent-space scalability for multi-task collaborative intelligence

arXiv: https://arxiv.org/abs/2105.10089 · HTML: https://mlsanity.com/paper/2105.10089/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2021.

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

- [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)
- [The JPEG Pleno Learning-based Point Cloud Coding Standard: Serving Man and Machine](https://mlsanity.com/paper/2409.08130/) (2024)
- [Joint Image Compression and Denoising via Latent-Space Scalability](https://mlsanity.com/paper/2205.01874/) (2022)
- [Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling](https://mlsanity.com/paper/2211.06797/) (2022)
- [DMOFC: Discrimination Metric-Optimized Feature Compression](https://mlsanity.com/paper/2405.04044/) (2024)
- [Learned Scalable Video Coding For Humans and Machines](https://mlsanity.com/paper/2307.08978/) (2023)
- [Base Layer Efficiency in Scalable Human-Machine Coding](https://mlsanity.com/paper/2307.02430/) (2023)
- [A New Image Codec Paradigm for Human and Machine Uses](https://mlsanity.com/paper/2112.10071/) (2021)
- [Multiscale Feature Importance-based Bit Allocation for End-to-End Feature Coding for Machines](https://mlsanity.com/paper/2503.19278/) (2025)
- [Compressed Feature Quality Assessment: Dataset and Baselines](https://mlsanity.com/paper/2506.07412/) (2025)
- [SFU-HW-Tracks-v1: Object Tracking Dataset on Raw Video Sequences](https://mlsanity.com/paper/2112.14934/) (2021)
- [Conditional and Residual Methods in Scalable Coding for Humans and Machines](https://mlsanity.com/paper/2305.02562/) (2023)
- [Towards Large Model Feature Coding](https://mlsanity.com/paper/2605.24025/) (2026)
- [CI-ICM: Channel Importance-driven Learned Image Coding for Machines](https://mlsanity.com/paper/2604.05347/) (2026)
- [Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding](https://mlsanity.com/paper/2608.08832/) (2026)

## Abstract (arXiv)

We investigate latent-space scalability for multi-task collaborative intelligence, where one of the tasks is object detection and the other is input reconstruction. In our proposed approach, part of the latent space can be selectively decoded to support object detection while the remainder can be decoded when input reconstruction is needed. Such an approach allows reduced computational resources when only object detection is required, and this can be achieved without reconstructing input pixels. By varying the scaling factors of various terms in the training loss function, the system can be trained to achieve various trade-offs between object detection accuracy and input reconstruction quality. Experiments are conducted to demonstrate the adjustable system performance on the two tasks compared to the relevant benchmarks.