# Experience feedback using Representation Learning for Few-Shot Object Detection on Aerial Images

arXiv: https://arxiv.org/abs/2109.13027 · HTML: https://mlsanity.com/paper/2109.13027/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 27 Sep 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)
- [RepMet: Representative-based metric learning for classification and one-shot object detection](https://mlsanity.com/paper/1806.04728/) (2018)
- [LSTD: A Low-Shot Transfer Detector for Object Detection](https://mlsanity.com/paper/1803.01529/) (2018)
- [One-Shot Object Detection with Co-Attention and Co-Excitation](https://mlsanity.com/paper/1911.12529/) (2019)
- [Few-shot Object Detection on Remote Sensing Images](https://mlsanity.com/paper/2006.07826/) (2020)
- [Few-shot Object Detection with Self-adaptive Attention Network for Remote Sensing Images](https://mlsanity.com/paper/2009.12596/) (2020)
- [Few-Shot Object Detection via Knowledge Transfer](https://mlsanity.com/paper/2008.12496/) (2020)

## Built on by (most cited first, 3 of 3)

- [Rethinking Intersection Over Union for Small Object Detection in Few-Shot Regime](https://mlsanity.com/paper/2307.09562/) (2023)
- [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)

## Abstract (arXiv)

This paper proposes a few-shot method based on Faster R-CNN and representation learning for object detection in aerial images. The two classification branches of Faster R-CNN are replaced by prototypical networks for online adaptation to new classes. These networks produce embeddings vectors for each generated box, which are then compared with class prototypes. The distance between an embedding and a prototype determines the corresponding classification score. The resulting networks are trained in an episodic manner. A new detection task is randomly sampled at each epoch, consisting in detecting only a subset of the classes annotated in the dataset. This training strategy encourages the network to adapt to new classes as it would at test time. In addition, several ideas are explored to improve the proposed method such as a hard negative examples mining strategy and self-supervised clustering for background objects. The performance of our method is assessed on DOTA, a large-scale remote sensing images dataset. The experiments conducted provide a broader understanding of the capabilities of representation learning. It highlights in particular some intrinsic weaknesses for the few-shot object detection task. Finally, some suggestions and perspectives are formulated according to these insights.