# Trusting small training dataset for supervised change detection

arXiv: https://arxiv.org/abs/2104.05443 · HTML: https://mlsanity.com/paper/2104.05443/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 9 Apr 2021.

## Builds on (most cited first, 5 of 5)

- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks](https://mlsanity.com/paper/1810.08468/) (2018)
- [Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery](https://mlsanity.com/paper/1803.02642/) (2018)
- [Active Deep Learning for Classification of Hyperspectral Images](https://mlsanity.com/paper/1611.10031/) (2016)
- [Change Detection between Multimodal Remote Sensing Data Using Siamese CNN](https://mlsanity.com/paper/1807.09562/) (2018)

## Abstract (arXiv)

Deep learning (DL) based supervised change detection (CD) models require large labeled training data. Due to the difficulty of collecting labeled multi-temporal data, unsupervised methods are preferred in the CD literature. However, unsupervised methods cannot fully exploit the potentials of data-driven deep learning and thus they are not absolute alternative to the supervised methods. This motivates us to look deeper into the supervised DL methods and investigate how they can be adopted intelligently for CD by minimizing the requirement of labeled training data. Towards this, in this work we show that geographically diverse training dataset can yield significant improvement over less diverse training datasets of the same size. We propose a simple confidence indicator for verifying the trustworthiness/confidence of supervised models trained with small labeled dataset. Moreover, we show that for the test cases where supervised CD model is found to be less confident/trustworthy, unsupervised methods often produce better result than the supervised ones.