# Few-Example Object Detection with Model Communication

arXiv: https://arxiv.org/abs/1706.08249 · HTML: https://mlsanity.com/paper/1706.08249/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2017.

## Built on by (most cited first, 12 of 12)

- [DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection](https://mlsanity.com/paper/2108.09017/) (2021)
- [Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection](https://mlsanity.com/paper/2103.01903/) (2021)
- [Hallucination Improves Few-Shot Object Detection](https://mlsanity.com/paper/2105.01294/) (2021)
- [Few-Shot Temporal Action Localization with Query Adaptive Transformer](https://mlsanity.com/paper/2110.10552/) (2021)
- [Semi-supervised Anatomical Landmark Detection via Shape-regulated Self-training](https://mlsanity.com/paper/2105.13593/) (2021)
- [VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments](https://mlsanity.com/paper/2207.11810/) (2022)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [A Survey of Deep Learning for Low-Shot Object Detection](https://mlsanity.com/paper/2112.02814/) (2021)
- [When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework](https://mlsanity.com/paper/2201.06781/) (2022)
- [Bootstrap Your Object Detector via Mixed Training](https://mlsanity.com/paper/2111.03056/) (2021)
- [Multi-Modal Few-Shot Temporal Action Detection](https://mlsanity.com/paper/2211.14905/) (2022)
- [Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?](https://mlsanity.com/paper/2403.02818/) (2024)

## Abstract (arXiv)

In this paper, we study object detection using a large pool of unlabeled images and only a few labeled images per category, named "few-example object detection". The key challenge consists in generating trustworthy training samples as many as possible from the pool. Using few training examples as seeds, our method iterates between model training and high-confidence sample selection. In training, easy samples are generated first and, then the poorly initialized model undergoes improvement. As the model becomes more discriminative, challenging but reliable samples are selected. After that, another round of model improvement takes place. To further improve the precision and recall of the generated training samples, we embed multiple detection models in our framework, which has proven to outperform the single model baseline and the model ensemble method. Experiments on PASCAL VOC'07, MS COCO'14, and ILSVRC'13 indicate that by using as few as three or four samples selected for each category, our method produces very competitive results when compared to the state-of-the-art weakly-supervised approaches using a large number of image-level labels.