# Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

arXiv: https://arxiv.org/abs/2303.12369 · HTML: https://mlsanity.com/paper/2303.12369/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 49 references that are in the map.
- First posted on arXiv 22 Mar 2023.

## Builds on (most cited first, 27 of 27)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Expanding Language-Image Pretrained Models for General Video Recognition](https://mlsanity.com/paper/2208.02816/) (2022)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection](https://mlsanity.com/paper/1903.07256/) (2019)
- [Understanding Self-Training for Gradual Domain Adaptation](https://mlsanity.com/paper/2002.11361/) (2020)
- [Cycle Self-Training for Domain Adaptation](https://mlsanity.com/paper/2103.03571/) (2021)
- [Interventional Few-Shot Learning](https://mlsanity.com/paper/2009.13000/) (2020)
- [Generative Cooperative Learning for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2203.03962/) (2022)
- [UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection](https://mlsanity.com/paper/2111.08644/) (2021)
- [Learning Deep Representations of Appearance and Motion for Anomalous Event Detection](https://mlsanity.com/paper/1510.01553/) (2015)
- [Learning Normal Dynamics in Videos with Meta Prototype Network](https://mlsanity.com/paper/2104.06689/) (2021)
- [GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection](https://mlsanity.com/paper/1908.05884/) (2019)
- [Localizing Anomalies from Weakly-Labeled Videos](https://mlsanity.com/paper/2008.08944/) (2020)
- [Unmasking the abnormal events in video](https://mlsanity.com/paper/1705.08182/) (2017)
- [Motion-Aware Feature for Improved Video Anomaly Detection](https://mlsanity.com/paper/1907.10211/) (2019)
- [Transporting Causal Mechanisms for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.11055/) (2021)
- [Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection](https://mlsanity.com/paper/1610.00307/) (2016)
- [Subspace Support Vector Data Description](https://mlsanity.com/paper/1802.03989/) (2018)
- [A Discriminative Framework for Anomaly Detection in Large Videos](https://mlsanity.com/paper/1609.08938/) (2016)
- [Real-Time Anomaly Detection and Localization in Crowded Scenes](https://mlsanity.com/paper/1511.06936/) (2015)
- [Global Information Guided Video Anomaly Detection](https://mlsanity.com/paper/2104.06813/) (2021)

## Built on by (most cited first, 30 of 64)

- [VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2308.11681/) (2023)
- [Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity](https://mlsanity.com/paper/2412.06171/) (2024)
- [Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM](https://mlsanity.com/paper/2406.12235/) (2024)
- [Open-Vocabulary Video Anomaly Detection](https://mlsanity.com/paper/2311.07042/) (2023)
- [Video Anomaly Detection and Explanation via Large Language Models](https://mlsanity.com/paper/2401.05702/) (2024)
- [Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2306.14451/) (2023)
- [Deep Learning for Video Anomaly Detection: A Review](https://mlsanity.com/paper/2409.05383/) (2024)
- [Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection](https://mlsanity.com/paper/2310.12790/) (2023)
- [VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models](https://mlsanity.com/paper/2412.01095/) (2024)
- [Video Anomaly Detection in 10 Years: A Survey and Outlook](https://mlsanity.com/paper/2405.19387/) (2024)
- [VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree](https://mlsanity.com/paper/2510.22693/) (2025)
- [Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attention](https://mlsanity.com/paper/2309.16309/) (2023)
- [Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities](https://mlsanity.com/paper/2406.08379/) (2024)
- [Anomize: Better Open Vocabulary Video Anomaly Detection](https://mlsanity.com/paper/2503.18094/) (2025)
- [Privacy-Preserving Video Anomaly Detection: A Survey](https://mlsanity.com/paper/2411.14565/) (2024)
- [Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detection](https://mlsanity.com/paper/2503.03562/) (2025)
- [Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly](https://mlsanity.com/paper/2412.07183/) (2024)
- [Anomaly Detection and Generation with Diffusion Models: A Survey](https://mlsanity.com/paper/2506.09368/) (2025)
- [GlanceVAD: Exploring Glance Supervision for Label-efficient Video Anomaly Detection](https://mlsanity.com/paper/2403.06154/) (2024)
- [Vision-Language Models Assisted Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2409.14109/) (2024)
- [Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection](https://mlsanity.com/paper/2412.03044/) (2024)
- [Mixture of Experts Guided by Gaussian Splatters Matters: A new Approach to Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2508.06318/) (2025)
- [Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2401.13551/) (2024)
- [Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Method](https://mlsanity.com/paper/2501.07496/) (2025)
- [Multi-Instance Partial-Label Learning with Margin Adjustment](https://mlsanity.com/paper/2501.12597/) (2025)
- [A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding](https://mlsanity.com/paper/2505.21962/) (2025)
- [The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM](https://mlsanity.com/paper/2507.21649/) (2025)
- [VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models](https://mlsanity.com/paper/2511.07299/) (2025)
- [Just Dance with π! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection](https://mlsanity.com/paper/2505.13123/) (2025)
- [Rethinking Metrics and Benchmarks of Video Anomaly Detection](https://mlsanity.com/paper/2505.19022/) (2025)

## Abstract (arXiv)

Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because the binary anomaly label is only given on the video level, but the output requires snippet-level predictions. So, Multiple Instance Learning (MIL) is prevailing in WSVAD. However, MIL is notoriously known to suffer from many false alarms because the snippet-level detector is easily biased towards the abnormal snippets with simple context, confused by the normality with the same bias, and missing the anomaly with a different pattern. To this end, we propose a new MIL framework: Unbiased MIL (UMIL), to learn unbiased anomaly features that improve WSVAD. At each MIL training iteration, we use the current detector to divide the samples into two groups with different context biases: the most confident abnormal/normal snippets and the rest ambiguous ones. Then, by seeking the invariant features across the two sample groups, we can remove the variant context biases. Extensive experiments on benchmarks UCF-Crime and TAD demonstrate the effectiveness of our UMIL. Our code is provided at https://github.com/ktr-hubrt/UMIL.