Deep learning has revolutionized object detection thanks to large-scale datasets, but their object categories are still arguably very limited. In this paper, we attempt to enrich such categories by addressing the one-shot object detection problem, where the number of annotated training examples for learning an unseen class is limited to one. We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module, the combination of which integrates metric learning with an anchor-free Faster R-CNN-style detection pipeline, eventually eliminating the need to fine-tune on the support images. We also propose novel training strategies that effectively improve detection performance. Extensive quantitative and qualitative evaluations were performed and our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
@article{arxiv.2005.03819,
title = {One-Shot Object Detection without Fine-Tuning},
author = {Xiang Li and Lin Zhang and Yau Pun Chen and Yu-Wing Tai and Chi-Keung Tang},
journal= {arXiv preprint arXiv:2005.03819},
year = {2020}
}