Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation

In recent times, following the paradigm of DETR (DEtection TRansformer), query-based end-to-end instance segmentation (QEIS) methods have exhibited superior performance compared to CNN-based models, particularly when trained on large-scale datasets. Nevertheless, the effectiveness of these QEIS meth...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Zhang, Dingwen, Li, Hao, He, Diqi, Liu, Nian, Cheng, Lechao, Wang, Jingdong, Han, Junwei
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!