# Rare Event Detection using Disentangled Representation Learning

arXiv: https://arxiv.org/abs/1812.01285 · HTML: https://mlsanity.com/paper/1812.01285/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2018.

## Built on by (most cited first, 12 of 12)

- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Backdoor Defense via Deconfounded Representation Learning](https://mlsanity.com/paper/2303.06818/) (2023)
- [Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization](https://mlsanity.com/paper/2206.11493/) (2022)
- [A Comprehensive Survey on Rare Event Prediction](https://mlsanity.com/paper/2309.11356/) (2023)
- [Semi-supervised Deep Learning for Image Classification with Distribution Mismatch: A Survey](https://mlsanity.com/paper/2203.00190/) (2022)
- [FrameHopper: Selective Processing of Video Frames in Detection-driven Real-Time Video Analytics](https://mlsanity.com/paper/2203.11493/) (2022)
- [Learning Actionable World Models for Industrial Process Control](https://mlsanity.com/paper/2503.01411/) (2025)
- [Dealing with Distribution Mismatch in Semi-supervised Deep Learning for Covid-19 Detection Using Chest X-ray Images: A Novel Approach Using Feature Densities](https://mlsanity.com/paper/2109.00889/) (2021)
- [Evaluating the Role of Data Enrichment Approaches Towards Rare Event Analysis in Manufacturing](https://mlsanity.com/paper/2407.01644/) (2024)
- [Differencing based Self-supervised pretraining for Scene Change Detection](https://mlsanity.com/paper/2208.05838/) (2022)
- [Prototype-oriented Unsupervised Change Detection for Disaster Management](https://mlsanity.com/paper/2310.09759/) (2023)
- [CLEAR: Unlearning Spurious Style-Content Associations with Contrastive LEarning with Anti-contrastive Regularization](https://mlsanity.com/paper/2507.18794/) (2025)

## Abstract (arXiv)

This paper presents a novel method for rare event detection from an image pair with class-imbalanced datasets. A straightforward approach for event detection tasks is to train a detection network from a large-scale dataset in an end-to-end manner. However, in many applications such as building change detection on satellite images, few positive samples are available for the training. Moreover, scene image pairs contain many trivial events, such as in illumination changes or background motions. These many trivial events and the class imbalance problem lead to false alarms for rare event detection. In order to overcome these difficulties, we propose a novel method to learn disentangled representations from only low-cost negative samples. The proposed method disentangles different aspects in a pair of observations: variant and invariant factors that represent trivial events and image contents, respectively. The effectiveness of the proposed approach is verified by the quantitative evaluations on four change detection datasets, and the qualitative analysis shows that the proposed method can acquire the representations that disentangle rare events from trivial ones.