MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1109/tip.2025.3641316

Медицинская библиотека · IEEE transactions on image processing : a publication of the IEEE Signal Processing Society · 2025

Vision-Language Models Empowered Nighttime Object Detection With Consistency Sampler and Hallucination Feature Generator.

He Lihuo, Ke Junjie, Wang Zhenghao, Li Jie, Zhou Kai, Wang Qi, Gao Xinbo

СтатьяПеревод в очереди

Аннотация

Current object detectors often suffer performance degradation when applied to cross-domain scenarios, particularly under challenging visual conditions such as nighttime scenes. This is primarily due to the I3 problems: Inadequate sampling of instance-level features, Indistinguishable feature representation across domains and Inaccurate generation for identical category participation. To address these challenges, we propose a domain-adaptive detection framework that enables robust generalization across different visual domains without introducing any additional inference overhead. The framework comprises three key components. Specifically, the centerness-category consistency sampler alleviates inadequate sampling by selecting representative instance-level features, while the paired centerness consistency loss enforces alignment between classification and localization. Second, VLM-based orthogonality enhancement leverages frozen vision-language encoders with an orthogonal projection loss to improve cross-domain feature distinguishability. Third, hallucination feature generator synthesizes robust instance-level features for missing categories, ensuring balanced category participation across domains. Extensive experiments on multiple datasets covering various domain adaptation and generalization settings demonstrate that our method consistently outperforms state-of-the-art detectors, achieving up to 5.5 mAP improvement, with particularly strong gains in nighttime adaptation.

Для цитирования: He Lihuo, Ke Junjie, Wang Zhenghao, Li Jie, Zhou Kai, Wang Qi, Gao Xinbo. Vision-Language Models Empowered Nighttime Object Detection With Consistency Sampler and Hallucination Feature Generator.. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2025. DOI: 10.1109/tip.2025.3641316.
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.