# Guided Anisotropic Diffusion and Iterative Learning for Weakly Supervised Change Detection

## TL;DR

This paper introduces an iterative learning approach combined with guided anisotropic diffusion to enhance weakly supervised change detection, effectively handling noisy datasets and improving segmentation accuracy.

## Contribution

It proposes a novel iterative training method and a guided anisotropic diffusion algorithm to improve change detection performance on noisy, large-scale datasets.

## Key findings

- Surpasses naive supervised learning performance
- Effective noise reduction in large datasets
- Improved semantic segmentation accuracy

## Abstract

Large scale datasets created from user labels or openly available data have become crucial to provide training data for large scale learning algorithms. While these datasets are easier to acquire, the data are frequently noisy and unreliable, which is motivating research on weakly supervised learning techniques. In this paper we propose an iterative learning method that extracts the useful information from a large scale change detection dataset generated from open vector data to train a fully convolutional network which surpasses the performance obtained by naive supervised learning. We also propose the guided anisotropic diffusion algorithm, which improves semantic segmentation results using the input images as guides to perform edge preserving filtering, and is used in conjunction with the iterative training method to improve results.