# InDiD: Instant Disorder Detection via Representation Learning

arXiv: https://arxiv.org/abs/2106.02602 · HTML: https://mlsanity.com/paper/2106.02602/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 4 Jun 2021.

## Builds on (most cited first, 18 of 18)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video](https://mlsanity.com/paper/1812.04960/) (2018)
- [Oops! Predicting Unintentional Action in Video](https://mlsanity.com/paper/1911.11206/) (2019)
- [Temporal Recurrent Networks for Online Action Detection](https://mlsanity.com/paper/1811.07391/) (2018)
- [An Evaluation of Change Point Detection Algorithms](https://mlsanity.com/paper/2003.06222/) (2020)
- [Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding](https://mlsanity.com/paper/2011.14097/) (2020)
- [Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series](https://mlsanity.com/paper/1809.04758/) (2018)
- [Kernel Change-point Detection with Auxiliary Deep Generative Models](https://mlsanity.com/paper/1901.06077/) (2019)
- [Scan B-Statistic for Kernel Change-Point Detection](https://mlsanity.com/paper/1507.01279/) (2015)
- [High-dimensional, multiscale online changepoint detection](https://mlsanity.com/paper/2003.03668/) (2020)
- [Selective review of offline change point detection methods](https://mlsanity.com/paper/1801.00718/) (2018)
- [Online Neural Networks for Change-Point Detection](https://mlsanity.com/paper/2010.01388/) (2020)
- [Real-time data-driven detection of the rock type alteration during a directional drilling](https://mlsanity.com/paper/1903.11436/) (2019)
- [Semi-supervised sequence classification through change point detection](https://mlsanity.com/paper/2009.11829/) (2020)

## Built on by (most cited first, 4 of 4)

- [Learning Transactions Representations for Information Management in Banks: Mastering Local, Global, and External Knowledge](https://mlsanity.com/paper/2404.02047/) (2024)
- [Normalizing self-supervised learning for provably reliable Change Point Detection](https://mlsanity.com/paper/2410.13637/) (2024)
- [Distribution estimation and change-point estimation for time series via DNN-based GANs](https://mlsanity.com/paper/2211.14577/) (2022)
- [WWAggr: A Window Wasserstein-based Aggregation for Ensemble Change Point Detection](https://mlsanity.com/paper/2506.08066/) (2025)

## Abstract (arXiv)

For sequential data, a change point is a moment of abrupt regime switch in data streams. Such changes appear in different scenarios, including simpler data from sensors and more challenging video surveillance data. We need to detect disorders as fast as possible. Classic approaches for change point detection (CPD) might underperform for semi-structured sequential data because they cannot process its structure without a proper representation. We propose a principled loss function that balances change detection delay and time to a false alarm. It approximates classic rigorous solutions but is differentiable and allows representation learning for deep models. We consider synthetic sequences, real-world data sensors and videos with change points. We carefully labelled available data with change point moments for video data and released it for the first time. Experiments suggest that complex data require meaningful representations tailored for the specificity of the CPD task -- and our approach provides them outperforming considered baselines. For example, for explosion detection in video, the F1 score for our method is 0.53 compared to baseline scores of 0.31 and 0.35.