# Few-shot Multispectral Segmentation with Representations Generated by Reinforcement Learning

arXiv: https://arxiv.org/abs/2311.11827 · HTML: https://mlsanity.com/paper/2311.11827/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 20 Nov 2023.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Thinking Fast and Slow with Deep Learning and Tree Search](https://mlsanity.com/paper/1705.08439/) (2017)
- [Data augmentation using learned transformations for one-shot medical image segmentation](https://mlsanity.com/paper/1902.09383/) (2019)
- [Reinforcement Learning of Theorem Proving](https://mlsanity.com/paper/1805.07563/) (2018)
- [Image Deformation Meta-Networks for One-Shot Learning](https://mlsanity.com/paper/1905.11641/) (2019)
- [Few-Shot Learning via Saliency-guided Hallucination of Samples](https://mlsanity.com/paper/1904.03472/) (2019)
- [LaSO: Label-Set Operations networks for multi-label few-shot learning](https://mlsanity.com/paper/1902.09811/) (2019)
- [Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning](https://mlsanity.com/paper/1703.06452/) (2017)
- [Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection](https://mlsanity.com/paper/2206.00515/) (2022)

## Abstract (arXiv)

The task of segmentation of multispectral images, which are images with numerous channels or bands, each capturing a specific range of wavelengths of electromagnetic radiation, has been previously explored in contexts with large amounts of labeled data. However, these models tend not to generalize well to datasets of smaller size. In this paper, we propose a novel approach for improving few-shot segmentation performance on multispectral images using reinforcement learning to generate representations. These representations are generated as mathematical expressions between channels and are tailored to the specific class being segmented. Our methodology involves training an agent to identify the most informative expressions using a small dataset, which can include as few as a single labeled sample, updating the dataset using these expressions, and then using the updated dataset to perform segmentation. Due to the limited length of the expressions, the model receives useful representations without any added risk of overfitting. We evaluate the effectiveness of our approach on samples of several multispectral datasets and demonstrate its effectiveness in boosting the performance of segmentation algorithms in few-shot contexts. The code is available at https://github.com/dilithjay/IndexRLSeg.