Back to search

CSUniversity San Bernardino

ROBUST MULTI-OBJECT DETECTION UNDER LOW-LIGHT CONDITIONS: A COMPARATIVE STUDY OF TRANSFORMER-BASED DETECTORS WITH LOW-LIGHT AUGMENTED FINE-TUNING

Abstract

dc:description.abstract

Object detection in low-light environments remains a significant challenge for modern computer vision systems. This paper presents a systematic comparative study of three state-of-the-art transformer-based object detection architectures — DETR (DEtection TRansformer), YOLOS (You Only Look at One Sequence), and RT-DETR (Real-Time DEtection TRansformer) — evaluated under both normal and degraded lighting conditions. We propose a three-phase experimental methodology: (1) pretrained baseline evaluation, (2) fine-tuning with low-light augmented training data, and (3) dual test set evaluation under normal and simulated low-light conditions. Our experiments on the COCO val2017 dataset demonstrate that low-light augmented fine-tuning yields substantial improvements across all three architectures, with YOLOS-Small achieving the largest relative improvement (+991% mAP increase) and RT-DETR-R50 maintaining the highest absolute performance (mAP = 0.1232 on normal, 0.1227 on low-light). Notably, all models exhibit strong robustness to low-light degradation after augmented training, with minimal performance gaps between normal and low-light evaluation conditions. These findings suggest that data augmentation strategies incorporating synthetic low-light simulation are an effective and architecture-agnostic approach to improving detection robustness in challenging illumination scenarios.

Degree

thesis:*
Name thesis:degree_name
Master of Science in Computer Science
Level thesis:degree_level
Restricted Project: Campus only access
Discipline thesis:degree_discipline
School of Computer Science and Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zhang, Naiqi
Contributors dc:contributor
  • Yan Zhang

Subjects

dc:subject × 7

Identifiers

dc:identifier.*
Repository record dc:identifier
https://scholarworks.lib.csusb.edu/etd/2415

Chain of custody

source
Harvested from
CSUniversity San Bernardino
Base URL
scholarworks.lib.csusb.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Zhang, Naiqi. ROBUST MULTI-OBJECT DETECTION UNDER LOW-LIGHT CONDITIONS: A COMPARATIVE STUDY OF TRANSFORMER-BASED DETECTORS WITH LOW-LIGHT AUGMENTED FINE-TUNING. Restricted Project: Campus only access thesis, https://scholarworks.lib.csusb.edu/etd/2415