# CI-ICM: Channel Importance-driven Learned Image Coding for Machines

arXiv: https://arxiv.org/abs/2604.05347 · HTML: https://mlsanity.com/paper/2604.05347/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 24 of 24)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things](https://mlsanity.com/paper/2011.08612/) (2020)
- [MLIC: Multi-Reference Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2211.07273/) (2022)
- [Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics](https://mlsanity.com/paper/2001.03569/) (2020)
- [Scalable Image Coding for Humans and Machines](https://mlsanity.com/paper/2107.08373/) (2021)
- [Image coding for machines: an end-to-end learned approach](https://mlsanity.com/paper/2108.09993/) (2021)
- [End-to-end Learning of Compressible Features](https://mlsanity.com/paper/2007.11797/) (2020)
- [TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception](https://mlsanity.com/paper/2306.05085/) (2023)
- [End-to-end optimized image compression for machines, a study](https://mlsanity.com/paper/2011.06409/) (2020)
- [Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation](https://mlsanity.com/paper/2407.09853/) (2024)
- [Visual Analysis Motivated Rate-Distortion Model for Image Coding](https://mlsanity.com/paper/2104.10315/) (2021)
- [Learned Image Coding for Machines: A Content-Adaptive Approach](https://mlsanity.com/paper/2108.09992/) (2021)
- [Just Noticeable Difference for Deep Machine Vision](https://mlsanity.com/paper/2102.08168/) (2021)
- [Latent-space scalability for multi-task collaborative intelligence](https://mlsanity.com/paper/2105.10089/) (2021)
- [Image Coding for Machines with Edge Information Learning Using Segment Anything](https://mlsanity.com/paper/2403.04173/) (2024)
- [SC2 Benchmark: Supervised Compression for Split Computing](https://mlsanity.com/paper/2203.08875/) (2022)
- [Rate-Distortion Theory in Coding for Machines and its Application](https://mlsanity.com/paper/2305.17295/) (2023)
- [End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization](https://mlsanity.com/paper/2107.00328/) (2021)
- [On Biasing Transformer Attention Towards Monotonicity](https://mlsanity.com/paper/2104.03945/) (2021)
- [Learned Disentangled Latent Representations for Scalable Image Coding for Humans and Machines](https://mlsanity.com/paper/2301.04183/) (2023)
- [Multiscale Feature Importance-based Bit Allocation for End-to-End Feature Coding for Machines](https://mlsanity.com/paper/2503.19278/) (2025)

## Abstract (arXiv)

Traditional human vision-centric image compression methods are suboptimal for machine vision centric compression due to different visual properties and feature characteristics. To address this problem, we propose a Channel Importance-driven learned Image Coding for Machines (CI-ICM), aiming to maximize the performance of machine vision tasks at a given bitrate constraint. First, we propose a Channel Importance Generation (CIG) module to quantify channel importance in machine vision and develop a channel order loss to rank channels in descending order. Second, to properly allocate bitrate among feature channels, we propose a Feature Channel Grouping and Scaling (FCGS) module that non-uniformly groups the feature channels based on their importance and adjusts the dynamic range of each group. Based on FCGS, we further propose a Channel Importance-based Context (CI-CTX) module to allocate bits among feature groups and to preserve higher fidelity in critical channels. Third, to adapt to multiple machine tasks, we propose a Task-Specific Channel Adaptation (TSCA) module to adaptively enhance features for multiple downstream machine tasks. Experimental results on the COCO2017 dataset show that the proposed CI-ICM achieves BD-mAP@50:95 gains of 16.25% in object detection and 13.72% in instance segmentation over the established baseline codec. Ablation studies validate the effectiveness of each contribution, and computation complexity analysis reveals the practicability of the CI-ICM. This work establishes feature channel optimization for machine vision-centric compression, bridging the gap between image coding and machine perception.