AMIEOD: Adaptive Multi-Experts Image Enhancement for Object Detection in Low-Illumination Scenes

2026-05-07

AI Summary

This work addresses the significant degradation of object detection performance under low-light conditions by proposing a detection-oriented joint optimization framework. The framework incorporates a Multi-Expert Image Enhancement Module (MEIEM) that adaptively improves image quality, guided by a Detection-Guided Regression Loss (DGRL) and a Detection-Guided Cross-Entropy Loss (DGCE). An Expert Selection Module (ESM) dynamically aligns the enhancement strategy with the detection objective by selecting the most suitable expert based on scene content. Evaluated on multiple low-light benchmarks, the proposed method substantially outperforms existing object detection algorithms, achieving notable gains in detection accuracy while maintaining robustness across diverse illumination conditions.

Abstract

In multimedia application scenarios, images captured under low-illumination conditions often lead to lower accuracy in visual perception tasks compared to those taken in well-lit environments. To tackle this challenge, we propose AMIEOD, an image enhancement-enabled object detection framework for low-illumination scenes, where the two tasks are jointly optimized in a detection performance-oriented manner. Specifically, to fully exploit the information in poorly lit images, a Multi-Experts Image Enhancement Module (MEIEM) is proposed, which leverages diverse enhancement strategies. On this basis, aiming to better align the MEIEM with the detection task, we propose a Detection-Guided Regression Loss (DGRL) that utilizes the detection result to decide the regression target. Moreover, to dynamically select the most suitable enhancement strategy from MEIEM during inference, we construct an Expert Selection Module (ESM) guided by the proposed Detection-Guided Cross-Entropy (DGCE) loss, which formulates the optimization of ESM as a classification task. The improved method is well-matched with current detection algorithms to improve their performance in dim scenes. Extensive experiments on multiple datasets demonstrate that the proposed method significantly improves object detection accuracy in low-illumination conditions. Our code has been released at https://github.com/scujayfantasy/AMIEOD

Problem

• low-illumination
• object detection
• image enhancement
• visual perception
• multimedia applications

Innovation

• Multi-Experts Image Enhancement
• Detection-Guided Regression Loss
• Expert Selection Module
• Low-Illumination Object Detection
• Joint Optimization