Saved in:
Bibliographic Details
Main Authors: Du, Zhipeng, Shi, Miaojing, Deng, Jiankang
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.01220
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914730516414464
author Du, Zhipeng
Shi, Miaojing
Deng, Jiankang
author_facet Du, Zhipeng
Shi, Miaojing
Deng, Jiankang
contents 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. Revisiting Retinex theory in the low-level vision, we first design 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_01220
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation
Du, Zhipeng
Shi, Miaojing
Deng, Jiankang
Computer Vision and Pattern Recognition
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. Revisiting Retinex theory in the low-level vision, we first design 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.
title Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.01220