10 papers
RegionDet: A Benchmark for Region Detection Beyond Object Instances
Liang Wan, Yuhan Wang, Yupeng Zhang +4
Object detection is a fundamental task in computer vision and has achieved remarkable progress on standard benchmarks by localizing discrete and well-bounded object instances. Howe…
ECAD: Expanding Class-Agnostic Detection Beyond Thing-Centric Objectness
Liang Wan, Zixin Ren, Yupeng Zhang +2
Object detection is a fundamental task in visual perception, providing structured region representations for recognition, grounding, reasoning, and interaction. However, existing d…
RT-SDGOD: Real-Time Single-Domain Generalized Object Detection
Yupeng Zhang, Fangzhuo Gao, Ruize Han +2
In real-world deployment under strict real-time constraints, weather and imaging variations induce significant distribution shifts, severely degrading detectors. Single-Domain Gene…
ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification
Yupeng Zhang, Yuzhong Feng, Ruize Han +3
Open-domain open-vocabulary detection (ODOVD) requires detectors to generalize to both novel categories and unseen domains, making it more challenging than open-vocabulary detectio…
LV-OSD: Language-Vision-Complementary Open-Set Object Detection
Yupeng Zhang, Ruize Han, Wei Feng +2
Object detection is an important task in computer vision, which aims to detect the objects of interest. through the given category list or query images. In this work, we propose a…
COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection
Yupeng Zhang, Ruize Han, Yuzhong Feng +3
Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-world category spaces continual…