eess.IVOct 30, 2026

IGDA-ICMH: an Importance Guided Feature and Network Dual Adaptation Framework towards Image Compression for Machine and Human Vision

Authors: Yanbo Gao, Xinyu Zhao, Shuai Li, Xun Cai, Mao Ye, Li Li

Organizations: School of Software, Shandong University, Jinan 250100, China, and also with Shandong University-WeiHai Research Institute of Industrial Technology, Weihai 264209, China. · School of Control Science and Engineering, Shandong University, Jinan 250100, China. · University of Electronic Science and Technology of China, Sichuan, China. · University of Science and Technology of China (USTC), Hefei, Anhui, China.

Abstract

With the surge of machine vision applications, image compression for both machine and human vision (ICMH) has become an important research area. Existing studies mainly focus on task-specific adaptation or multi-task joint optimization, yet they often overlook the unequal contributions of different features and network layers to downstream machine vision tasks. To address this issue, we first quantitatively investigate the impact of different feature and network layers on machine vision performance, providing a principled understanding of their importance. Based on this analysis, an Importance Guided feature and network Dual Adaptation (IGDA) framework is developed for ICMH. It adopts implicit neural representation as the basic architecture and designs an efficient adaptation structure with both feature and network weight adaptation. An Importance-Guided Network Adaptation (IGNA) module is developed with a low-rank adaptation strategy to selectively adjust key network layers according to their importance in different tasks. An Importance-Guided Feature Adaptation (IGFA) module is developed with a low-rank and Kronecker product-based transform to explore the non-local property of the features in order to reduce the number of adaptation parameters. Extensive experiments on representative machine vision tasks, including image classification and object detection, demonstrate that our IGDA-ICMH framework achieves significantly better performance than the existing implicit neural representation-based methods for ICMH.

Figures & tables

Explore similar work

CardsList
  1. CI-ICM: Channel Importance-driven Learned Image Coding for Machines

    Apr 7, 2026Yun Zhang, Junle Liu, Huan Zhang +3Task-Aware CompressionLearned Image Compression

  2. CrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision Compression

    Aug 26, 2026Haobo Xiong, Shaobo Liu, Kai Liu +1Parameter-Efficient Fine-TuningLearned Image Compression