# Learning Instance Representation Banks for Aerial Scene Classification

arXiv: https://arxiv.org/abs/2205.13744 · HTML: https://mlsanity.com/paper/2205.13744/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 27 May 2022.

## Builds on (most cited first, 9 of 9)

- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [Weakly Supervised Instance Segmentation using Class Peak Response](https://mlsanity.com/paper/1804.00880/) (2018)
- [Learning RoI Transformer for Detecting Oriented Objects in Aerial Images](https://mlsanity.com/paper/1812.00155/) (2018)
- [Multiple instance dense connected convolution neural network for aerial image scene classification](https://mlsanity.com/paper/1908.08156/) (2019)
- [MIML-FCN+: Multi-instance Multi-label Learning via Fully Convolutional Networks with Privileged Information](https://mlsanity.com/paper/1702.08681/) (2017)
- [Binary Patterns Encoded Convolutional Neural Networks for Texture Recognition and Remote Sensing Scene Classification](https://mlsanity.com/paper/1706.01171/) (2017)

## Abstract (arXiv)

Aerial scenes are more complicated in terms of object distribution and spatial arrangement than natural scenes due to the bird view, and thus remain challenging to learn discriminative scene representation. Recent solutions design textitlocal semantic descriptors so that region of interests (RoIs) can be properly highlighted. However, each local descriptor has limited description capability and the overall scene representation remains to be refined. In this paper, we solve this problem by designing a novel representation set named textitinstance representation bank (IRB), which unifies multiple local descriptors under the multiple instance learning (MIL) formulation. This unified framework is not trivial as all the local semantic descriptors can be aligned to the same scene scheme, enhancing the scene representation capability. Specifically, our IRB learning framework consists of a backbone, an instance representation bank, a semantic fusion module and a scene scheme alignment loss function. All the components are organized in an end-to-end manner. Extensive experiments on three aerial scene benchmarks demonstrate that our proposed method outperforms the state-of-the-art approaches by a large margin.