Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation

arXiv:2312.01220v2 Announce Type: replace
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, …

arxiv boosting cs.cv detection domain domain adaptation object type zero-shot