Simple Multi-dataset Detection
Simple Multi-dataset Detection
复制标题
DOI:
10.1109/cvpr52688.2022.00742
复制
发表时间:
2021-02
期刊:
影响因子:
--
通讯作者:
Xingyi Zhou;V. Koltun;Philipp Krähenbühl
中科院分区:
文献类型:
--
作者:
Xingyi Zhou;V. Koltun;Philipp Krähenbühl
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.