# HSONet:A Siamese foreground association-driven hard case sample optimization network for high-resolution remote sensing image change detection

arXiv: https://arxiv.org/abs/2402.16242 · HTML: https://mlsanity.com/paper/2402.16242/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 54 references that are in the map.
- First posted on arXiv 26 Feb 2024.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Fully Convolutional Siamese Networks for Change Detection](https://mlsanity.com/paper/1810.08462/) (2018)
- [Remote Sensing Image Change Detection with Transformers](https://mlsanity.com/paper/2103.00208/) (2021)
- [Grad-CAM: Why did you say that?](https://mlsanity.com/paper/1611.07450/) (2016)
- [DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images](https://mlsanity.com/paper/2003.03608/) (2020)
- [Learning to Measure Change: Fully Convolutional Siamese Metric Networks for Scene Change Detection](https://mlsanity.com/paper/1810.09111/) (2018)
- [FCCDN: Feature Constraint Network for VHR Image Change Detection](https://mlsanity.com/paper/2105.10860/) (2021)
- [Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works](https://mlsanity.com/paper/2211.08129/) (2022)
- [Super-resolution-based Change Detection Network with Stacked Attention Module for Images with Different Resolutions](https://mlsanity.com/paper/2103.00188/) (2021)
- [Resolving Class Imbalance in Object Detection with Weighted Cross Entropy Losses](https://mlsanity.com/paper/2006.01413/) (2020)
- [Augmentation-Free Graph Contrastive Learning of Invariant-Discriminative Representations](https://mlsanity.com/paper/2210.08345/) (2022)
- [Fully Transformer Network for Change Detection of Remote Sensing Images](https://mlsanity.com/paper/2210.00757/) (2022)
- [GraSS: Contrastive Learning with Gradient Guided Sampling Strategy for Remote Sensing Image Semantic Segmentation](https://mlsanity.com/paper/2306.15868/) (2023)

## Abstract (arXiv)

In the later training stages, further improvement of the models ability to determine changes relies on how well the change detection (CD) model learns hard cases; however, there are two additional challenges to learning hard case samples: (1) change labels are limited and tend to pointer only to foreground targets, yet hard case samples are prevalent in the background, which leads to optimizing the loss function focusing on the foreground targets and ignoring the background hard cases, which we call imbalance. (2) Complex situations, such as light shadows, target occlusion, and seasonal changes, induce hard case samples, and in the absence of both supervisory and scene information, it is difficult for the model to learn hard case samples directly to accurately obtain the feature representations of the change information, which we call missingness. We propose a Siamese foreground association-driven hard case sample optimization network (HSONet). To deal with this imbalance, we propose an equilibrium optimization loss function to regulate the optimization focus of the foreground and background, determine the hard case samples through the distribution of the loss values, and introduce dynamic weights in the loss term to gradually shift the optimization focus of the loss from the foreground to the background hard cases as the training progresses. To address this missingness, we understand hard case samples with the help of the scene context, propose the scene-foreground association module, use potential remote sensing spatial scene information to model the association between the target of interest in the foreground and the related context to obtain scene embedding, and apply this information to the feature reinforcement of hard cases. Experiments on four public datasets show that HSONet outperforms current state-of-the-art CD methods, particularly in detecting hard case samples.