# Interactive Learning for Semantic Segmentation in Earth Observation

arXiv: https://arxiv.org/abs/2009.11250 · HTML: https://mlsanity.com/paper/2009.11250/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2020.

## Built on by (most cited first, 5 of 5)

- [DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensing](https://mlsanity.com/paper/2201.01047/) (2022)
- [Adapting the Segment Anything Model During Usage in Novel Situations](https://mlsanity.com/paper/2404.08421/) (2024)
- [DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation](https://mlsanity.com/paper/2506.23104/) (2025)
- [Weakly-supervised continual learning for class-incremental segmentation](https://mlsanity.com/paper/2201.01029/) (2022)
- [SkipClick: Combining Quick Responses and Low-Level Features for Interactive Segmentation in Winter Sports Contexts](https://mlsanity.com/paper/2501.07960/) (2025)

## Abstract (arXiv)

Dense pixel-wise classification maps output by deep neural networks are of extreme importance for scene understanding. However, these maps are often partially inaccurate due to a variety of possible factors. Therefore, we propose to interactively refine them within a framework named DISCA (Deep Image Segmentation with Continual Adaptation). It consists of continually adapting a neural network to a target image using an interactive learning process with sparse user annotations as ground-truth. We show through experiments on three datasets using synthesized annotations the benefits of the approach, reaching an IoU improvement up to 4.7% for ten sampled clicks. Finally, we exhibit that our approach can be particularly rewarding when it is faced to additional issues such as domain adaptation.