# Set Features for Fine-grained Anomaly Detection

arXiv: https://arxiv.org/abs/2302.12245 · HTML: https://mlsanity.com/paper/2302.12245/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 56 references that are in the map.
- First posted on arXiv 23 Feb 2023.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances](https://mlsanity.com/paper/2007.08176/) (2020)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings](https://mlsanity.com/paper/1911.02357/) (2019)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [Sub-Image Anomaly Detection with Deep Pyramid Correspondences](https://mlsanity.com/paper/2005.02357/) (2020)
- [Deep Semi-Supervised Anomaly Detection](https://mlsanity.com/paper/1906.02694/) (2019)
- [Multiresolution Knowledge Distillation for Anomaly Detection](https://mlsanity.com/paper/2011.11108/) (2020)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [Learning Representations for Automatic Colorization](https://mlsanity.com/paper/1603.06668/) (2016)
- [LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection](https://mlsanity.com/paper/1607.00148/) (2016)
- [Classification-Based Anomaly Detection for General Data](https://mlsanity.com/paper/2005.02359/) (2020)
- [MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification](https://mlsanity.com/paper/2012.08791/) (2020)
- [A review on outlier/anomaly detection in time series data](https://mlsanity.com/paper/2002.04236/) (2020)
- [DROCC: Deep Robust One-Class Classification](https://mlsanity.com/paper/2002.12718/) (2020)
- [Neural Transformation Learning for Deep Anomaly Detection Beyond Images](https://mlsanity.com/paper/2103.16440/) (2021)
- [Mean-Shifted Contrastive Loss for Anomaly Detection](https://mlsanity.com/paper/2106.03844/) (2021)
- [Learning Deep Features for One-Class Classification](https://mlsanity.com/paper/1801.05365/) (2018)
- [The Radon cumulative distribution transform and its application to image classification](https://mlsanity.com/paper/1511.03206/) (2015)
- [Collective Anomaly Detection based on Long Short Term Memory Recurrent Neural Network](https://mlsanity.com/paper/1703.09752/) (2017)
- [Transformaly -- Two (Feature Spaces) Are Better Than One](https://mlsanity.com/paper/2112.04185/) (2021)
- [Anomaly Detection Requires Better Representations](https://mlsanity.com/paper/2210.10773/) (2022)

## Built on by (most cited first, 13 of 13)

- [Towards Training-free Anomaly Detection with Vision and Language Foundation Models](https://mlsanity.com/paper/2503.18325/) (2025)
- [Component-aware anomaly detection framework for adjustable and logical industrial visual inspection](https://mlsanity.com/paper/2305.08509/) (2023)
- [Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection](https://mlsanity.com/paper/2303.05768/) (2023)
- [Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection](https://mlsanity.com/paper/2312.13783/) (2023)
- [Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2312.15911/) (2023)
- [REB: Reducing Biases in Representation for Industrial Anomaly Detection](https://mlsanity.com/paper/2308.12577/) (2023)
- [PUAD: Frustratingly Simple Method for Robust Anomaly Detection](https://mlsanity.com/paper/2402.15143/) (2024)
- [LogicAL: Towards logical anomaly synthesis for unsupervised anomaly localization](https://mlsanity.com/paper/2405.06875/) (2024)
- [Visual Anomaly Detection via Dual-Attention Transformer and Discriminative Flow](https://mlsanity.com/paper/2303.17882/) (2023)
- [MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detection](https://mlsanity.com/paper/2405.09933/) (2024)
- [Representation Learning in Anomaly Detection: Successes, Limits and a Grand Challenge](https://mlsanity.com/paper/2307.11085/) (2023)
- [Time-reversed Flow Matching with Worst Transport in High-dimensional Latent Space for Image Anomaly Detection](https://mlsanity.com/paper/2508.05461/) (2025)
- [HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detection](https://mlsanity.com/paper/2601.17405/) (2026)

## Abstract (arXiv)

Fine-grained anomaly detection has recently been dominated by segmentation based approaches. These approaches first classify each element of the sample (e.g., image patch) as normal or anomalous and then classify the entire sample as anomalous if it contains anomalous elements. However, such approaches do not extend to scenarios where the anomalies are expressed by an unusual combination of normal elements. In this paper, we overcome this limitation by proposing set features that model each sample by the distribution its elements. We compute the anomaly score of each sample using a simple density estimation method. Our simple-to-implement approach outperforms the state-of-the-art in image-level logical anomaly detection (+3.4%) and sequence-level time-series anomaly detection (+2.4%).