Low-Light Enhancement Effect on Classification and Detection: An Empirical Study

TL;DR

This paper empirically investigates how low-light image enhancement methods affect high-level vision tasks like classification and detection, revealing that improvements for human perception may not benefit or could hinder machine analysis.

Contribution

It provides a comprehensive empirical evaluation of LLIE methods on classification and detection, highlighting the disconnect between human-centric enhancement and machine vision performance.

Findings

LLIE methods improve human visual quality but have inconsistent effects on machine vision tasks.

Some LLIE techniques can even degrade classification and detection accuracy.

The study emphasizes the need for LLIE methods tailored to high-level vision tasks.

Abstract

Low-light images are commonly encountered in real-world scenarios, and numerous low-light image enhancement (LLIE) methods have been proposed to improve the visibility of these images. The primary goal of LLIE is to generate clearer images that are more visually pleasing to humans. However, the impact of LLIE methods in high-level vision tasks, such as image classification and object detection, which rely on high-quality image datasets, is not well {explored}. To explore the impact, we comprehensively evaluate LLIE methods on these high-level vision tasks by utilizing an empirical investigation comprising image classification and object detection experiments. The evaluation reveals a dichotomy: {\textit{While Low-Light Image Enhancement (LLIE) methods enhance human visual interpretation, their effect on computer vision tasks is inconsistent and can sometimes be harmful. }} Our findings suggest a disconnect between image enhancement for human visual perception and for machine analysis, indicating a need for LLIE methods tailored to support high-level vision tasks effectively. This insight is crucial for the development of LLIE techniques that align with the needs of both human and machine vision.