Open-vocabulary object detection via debiased curriculum self-training

• Main Authors: Zhang, Hanlue, Guan, Dayan, Ke, Xiangrui, El Saddik, Abdulmotaleb, Lu, Shijian
• Other Authors: College of Computing and Data Science
• Format: Article
• Language: English
• Published: 2024
• Subjects: Computer and Information Science; Object detection; Open-vocabulary recognition
• Online Access: https://hdl.handle.net/10356/180718
• Institution: Nanyang Technological University

Open-vocabulary object detection aims to train a detector capable of recognizing various novel classes. Most existing studies exploit image-level weak supervision to generate pseudo object boxes for novel class training. However, the generated pseudo boxes are often noisy and biased towards base cla...