Simple Multi-dataset Detection.

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2022)

引用 90|浏览186
暂无评分
摘要
How do we build a general and broad object detection system? We use all labels of all concepts ever annotated. These labels span diverse datasets with potentially inconsistent taxonomies. In this paper, we present a simple method for training a unified detector on multiple large-scale datasets. We use dataset-specific training protocols and losses, but share a common detection architecture with dataset-specific outputs. We show how to automatically integrate these dataset-specific outputs into a common semantic taxonomy. In contrast to prior work, our approach does not require manual taxonomy reconciliation. Experiments show our learned taxonomy outperforms a expert-designed taxonomy in all datasets. Our multi-dataset detector performs as well as dataset-specific models on each training domain, and can generalize to new unseen dataset without fine-tuning on them. Code is available at https://github.com/xingyizhou/UniDet.
更多
查看译文
关键词
Recognition: detection,categorization,retrieval
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要