English

Cross-dataset Training for Class Increasing Object Detection

Computer Vision and Pattern Recognition 2020-01-15 v1

Abstract

We present a conceptually simple, flexible and general framework for cross-dataset training in object detection. Given two or more already labeled datasets that target for different object classes, cross-dataset training aims to detect the union of the different classes, so that we do not have to label all the classes for all the datasets. By cross-dataset training, existing datasets can be utilized to detect the merged object classes with a single model. Further more, in industrial applications, the object classes usually increase on demand. So when adding new classes, it is quite time-consuming if we label the new classes on all the existing datasets. While using cross-dataset training, we only need to label the new classes on the new dataset. We experiment on PASCAL VOC, COCO, WIDER FACE and WIDER Pedestrian with both solo and cross-dataset settings. Results show that our cross-dataset pipeline can achieve similar impressive performance simultaneously on these datasets compared with training independently.

Keywords

Cite

@article{arxiv.2001.04621,
  title  = {Cross-dataset Training for Class Increasing Object Detection},
  author = {Yongqiang Yao and Yan Wang and Yu Guo and Jiaojiao Lin and Hongwei Qin and Junjie Yan},
  journal= {arXiv preprint arXiv:2001.04621},
  year   = {2020}
}

Comments

10 pages, 6 figures

R2 v1 2026-06-23T13:10:27.650Z