Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation

TL;DR

This paper introduces a novel low-light object detection method that leverages scene decomposition and semantic aggregation to turn ignored illumination into useful features, outperforming existing approaches.

Contribution

It proposes a new framework that extends illumination enhancers as scene decomposition modules and integrates multi-scale semantic information for improved low-light detection.

Findings

Outperforms state-of-the-art methods in low-light object detection

Effectively utilizes ignored illumination as auxiliary features

Demonstrates significant improvements in detection accuracy

Abstract

Object detection in low-light scenarios has attracted much attention in the past few years. A mainstream and representative scheme introduces enhancers as the pre-processing for regular detectors. However, because of the disparity in task objectives between the enhancer and detector, this paradigm cannot shine at its best ability. In this work, we try to arouse the potential of enhancer + detector. Different from existing works, we extend the illumination-based enhancers (our newly designed or existing) as a scene decomposition module, whose removed illumination is exploited as the auxiliary in the detector for extracting detection-friendly features. A semantic aggregation module is further established for integrating multi-scale scene-related semantic information in the context space. Actually, our built scheme successfully transforms the "trash" (i.e., the ignored illumination in the detector) into the "treasure" for the detector. Plenty of experiments are conducted to reveal our superiority against other state-of-the-art methods. The code will be public if it is accepted.