You Only Look Around: Learning Illumination Invariant Feature for Low-light Object Detection

TL;DR

This paper presents YOLA, a framework that learns illumination-invariant features for low-light object detection by exploiting the Lambertian model and spatial relationships, improving detection performance across lighting conditions.

Contribution

The paper introduces a novel module for learning illumination-invariant features based on the Lambertian model, integrated into detection networks for improved low-light object detection.

Findings

Significant improvement in low-light detection accuracy

Effective feature extraction under varying illumination conditions

Promising results in well-lit and over-lit scenarios

Abstract

In this paper, we introduce YOLA, a novel framework for object detection in low-light scenarios. Unlike previous works, we propose to tackle this challenging problem from the perspective of feature learning. Specifically, we propose to learn illumination-invariant features through the Lambertian image formation model. We observe that, under the Lambertian assumption, it is feasible to approximate illumination-invariant feature maps by exploiting the interrelationships between neighboring color channels and spatially adjacent pixels. By incorporating additional constraints, these relationships can be characterized in the form of convolutional kernels, which can be trained in a detection-driven manner within a network. Towards this end, we introduce a novel module dedicated to the extraction of illumination-invariant features from low-light images, which can be easily integrated into existing object detection frameworks. Our empirical findings reveal significant improvements in low-light object detection tasks, as well as promising results in both well-lit and over-lit scenarios. Code is available at \url{https://github.com/MingboHong/YOLA}.