# One-Shot Object Detection without Fine-Tuning

arXiv: https://arxiv.org/abs/2005.03819 · HTML: https://mlsanity.com/paper/2005.03819/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2020.

## Built on by (most cited first, 11 of 11)

- [A Survey of Self-Supervised and Few-Shot Object Detection](https://mlsanity.com/paper/2110.14711/) (2021)
- [Few-Shot Object Detection: A Comprehensive Survey](https://mlsanity.com/paper/2112.11699/) (2021)
- [Detect Everything with Few Examples](https://mlsanity.com/paper/2309.12969/) (2023)
- [Object Counting: You Only Need to Look at One](https://mlsanity.com/paper/2112.05993/) (2021)
- [A Comparative Review of Recent Few-Shot Object Detection Algorithms](https://mlsanity.com/paper/2111.00201/) (2021)
- [A Survey of Deep Learning for Low-Shot Object Detection](https://mlsanity.com/paper/2112.02814/) (2021)
- [Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga](https://mlsanity.com/paper/2410.05935/) (2024)
- [A Unified Framework for Attention-Based Few-Shot Object Detection](https://mlsanity.com/paper/2201.02052/) (2022)
- [A Comparative Attention Framework for Better Few-Shot Object Detection on Aerial Images](https://mlsanity.com/paper/2210.13923/) (2022)
- [SKU-Patch: Towards Efficient Instance Segmentation for Unseen Objects in Auto-Store](https://mlsanity.com/paper/2311.04645/) (2023)
- [Joint Neural Networks for One-shot Object Recognition and Detection](https://mlsanity.com/paper/2408.00701/) (2024)

## Abstract (arXiv)

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.