Boosting object detection with zero-shot day-night domain adaptation

Zhipeng Du, Miaojing Shi, Jiankang Deng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Detecting objects in low-light scenarios presents a persistent challenge, as detectors trained on well-lit data exhibit significant performance degradation on low-light data due to low visibility. Previous methods mitigate this issue by exploring image enhancement or object detection techniques with real low-light image datasets. However, the progress is impeded by the inherent difficulties about collecting and annotating low-light images. To address this challenge, we propose to boost low-light object detection with zero-shot day-night domain adaptation, which aims to generalize a detector from well-lit scenarios to low-light ones without requiring real low-light data. Re-visiting Retinex theory in the low-level vision, we first de-sign a reflectance representation learning module to learn Retinex-based illumination invariance in images with a carefully designed illumination invariance reinforcement strategy. Next, an interchange-redecomposition-coherence procedure is introduced to improve over the vanilla Retinex image decomposition process by performing two sequential image decompositions and introducing a redecomposition cohering loss. Extensive experiments on ExDark, DARK FACE, and CODaN datasets show strong low-light generalizability of our method. Our code is available at https://github.com/ZPDu/DAI-Net.
Original languageEnglish
Title of host publication2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherInstitute of Electrical and Electronics Engineers
Pages12666-12676
Number of pages11
ISBN (Electronic)9798350353006
ISBN (Print)9798350353013
DOIs
Publication statusPublished - 16 Sept 2024
EventThe Thirty-Fourth IEEE/CVF Conference on Computer Vision and Pattern Recognition - Seattle, United States
Duration: 17 Jun 202421 Jun 2024

Publication series

NameProceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

ConferenceThe Thirty-Fourth IEEE/CVF Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR 2024
Country/TerritoryUnited States
CitySeattle
Period17/06/2421/06/24

Keywords / Materials (for Non-textual outputs)

  • reflectivity
  • representation learning
  • degradation
  • face recognition
  • lighting
  • object detection
  • detectors

Fingerprint

Dive into the research topics of 'Boosting object detection with zero-shot day-night domain adaptation'. Together they form a unique fingerprint.

Cite this