# Backpropagated Gradient Representations for Anomaly Detection

arXiv: https://arxiv.org/abs/2007.09507 · HTML: https://mlsanity.com/paper/2007.09507/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2020.

## Built on by (most cited first, 30 of 54)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Open-Set Recognition: a Good Closed-Set Classifier is All You Need?](https://mlsanity.com/paper/2110.06207/) (2021)
- [A Unified Model for Multi-class Anomaly Detection](https://mlsanity.com/paper/2206.03687/) (2022)
- [Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2203.00259/) (2022)
- [Deep One-Class Classification via Interpolated Gaussian Descriptor](https://mlsanity.com/paper/2101.10043/) (2021)
- [Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2312.07495/) (2023)
- [Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need](https://mlsanity.com/paper/2302.02615/) (2023)
- [ADTR: Anomaly Detection Transformer with Feature Reconstruction](https://mlsanity.com/paper/2209.01816/) (2022)
- [Introspective Learning : A Two-Stage Approach for Inference in Neural Networks](https://mlsanity.com/paper/2209.08425/) (2022)
- [Gradient-Based Adversarial and Out-of-Distribution Detection](https://mlsanity.com/paper/2206.08255/) (2022)
- [CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoring](https://mlsanity.com/paper/2405.14737/) (2024)
- [Extracting Causal Visual Features for Limited label Classification](https://mlsanity.com/paper/2103.12322/) (2021)
- [Contrastive Reasoning in Neural Networks](https://mlsanity.com/paper/2103.12329/) (2021)
- [Explanatory Paradigms in Neural Networks](https://mlsanity.com/paper/2202.11838/) (2022)
- [Gaussian Switch Sampling: A Second Order Approach to Active Learning](https://mlsanity.com/paper/2302.12018/) (2023)
- [Probing the Purview of Neural Networks via Gradient Analysis](https://mlsanity.com/paper/2304.02834/) (2023)
- [Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models](https://mlsanity.com/paper/2312.02615/) (2023)
- [Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Data](https://mlsanity.com/paper/2301.05106/) (2023)
- [Open-Set Recognition with Gradient-Based Representations](https://mlsanity.com/paper/2206.08229/) (2022)
- [Man-recon: manifold learning for reconstruction with deep autoencoder for smart seismic interpretation](https://mlsanity.com/paper/2212.07568/) (2022)
- [Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videos](https://mlsanity.com/paper/2302.06670/) (2023)
- [Elsa: Energy-based learning for semi-supervised anomaly detection](https://mlsanity.com/paper/2103.15296/) (2021)
- [CVAD: A generic medical anomaly detector based on Cascade VAE](https://mlsanity.com/paper/2110.15811/) (2021)
- [Efficient Anomaly Detection Using Self-Supervised Multi-Cue Tasks](https://mlsanity.com/paper/2111.12379/) (2021)
- [A Gating Model for Bias Calibration in Generalized Zero-shot Learning](https://mlsanity.com/paper/2203.04195/) (2022)
- [Exploiting the Distortion-Semantic Interaction in Fisheye Data](https://mlsanity.com/paper/2305.00079/) (2023)
- [Exploring Transformers for Open-world Instance Segmentation](https://mlsanity.com/paper/2308.04206/) (2023)
- [Faithfulness Measurable Masked Language Models](https://mlsanity.com/paper/2310.07819/) (2023)
- [Example Forgetting: A Novel Approach to Explain and Interpret Deep Neural Networks in Seismic Interpretation](https://mlsanity.com/paper/2302.14644/) (2023)
- [Transitional Uncertainty with Layered Intermediate Predictions](https://mlsanity.com/paper/2405.17494/) (2024)

## Abstract (arXiv)

Learning representations that clearly distinguish between normal and abnormal data is key to the success of anomaly detection. Most of existing anomaly detection algorithms use activation representations from forward propagation while not exploiting gradients from backpropagation to characterize data. Gradients capture model updates required to represent data. Anomalies require more drastic model updates to fully represent them compared to normal data. Hence, we propose the utilization of backpropagated gradients as representations to characterize model behavior on anomalies and, consequently, detect such anomalies. We show that the proposed method using gradient-based representations achieves state-of-the-art anomaly detection performance in benchmark image recognition datasets. Also, we highlight the computational efficiency and the simplicity of the proposed method in comparison with other state-of-the-art methods relying on adversarial networks or autoregressive models, which require at least 27 times more model parameters than the proposed method.