# Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy

arXiv: https://arxiv.org/abs/2006.14811 · HTML: https://mlsanity.com/paper/2006.14811/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2020.

## Built on by (most cited first, 19 of 19)

- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Graph Neural Networks in Network Neuroscience](https://mlsanity.com/paper/2106.03535/) (2021)
- [Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes](https://mlsanity.com/paper/2111.12264/) (2021)
- [Deep One-Class Classification via Interpolated Gaussian Descriptor](https://mlsanity.com/paper/2101.10043/) (2021)
- [Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images](https://mlsanity.com/paper/2103.03423/) (2021)
- [ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image Classification](https://mlsanity.com/paper/2111.12918/) (2021)
- [Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Images](https://mlsanity.com/paper/2109.01303/) (2021)
- [Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection](https://mlsanity.com/paper/2203.12121/) (2022)
- [Unsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked Autoencoder](https://mlsanity.com/paper/2203.11725/) (2022)
- [Self-supervised Mean Teacher for Semi-supervised Chest X-ray Classification](https://mlsanity.com/paper/2103.03629/) (2021)
- [Frontiers in Intelligent Colonoscopy](https://mlsanity.com/paper/2410.17241/) (2024)
- [FewSOME: One-Class Few Shot Anomaly Detection with Siamese Networks](https://mlsanity.com/paper/2301.06957/) (2023)
- [Unsupervised Detection of Cancerous Regions in Histology Imagery using Image-to-Image Translation](https://mlsanity.com/paper/2104.13786/) (2021)
- [Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning](https://mlsanity.com/paper/2101.03285/) (2021)
- [Hard-Attention Gates with Gradient Routing for Endoscopic Image Computing](https://mlsanity.com/paper/2407.04400/) (2024)
- [A Few-shot Learning Graph Multi-Trajectory Evolution Network for Forecasting Multimodal Baby Connectivity Development from a Baseline Timepoint](https://mlsanity.com/paper/2110.03535/) (2021)
- [LesionPaste: One-Shot Anomaly Detection for Medical Images](https://mlsanity.com/paper/2203.06354/) (2022)
- [General-Purpose Multi-Modal OOD Detection Framework](https://mlsanity.com/paper/2307.13069/) (2023)
- [GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detection](https://mlsanity.com/paper/2510.20268/) (2025)

## Abstract (arXiv)

Anomaly detection methods generally target the learning of a normal image distribution (i.e., inliers showing healthy cases) and during testing, samples relatively far from the learned distribution are classified as anomalies (i.e., outliers showing disease cases). These approaches tend to be sensitive to outliers that lie relatively close to inliers (e.g., a colonoscopy image with a small polyp). In this paper, we address the inappropriate sensitivity to outliers by also learning from inliers. We propose a new few-shot anomaly detection method based on an encoder trained to maximise the mutual information between feature embeddings and normal images, followed by a few-shot score inference network, trained with a large set of inliers and a substantially smaller set of outliers. We evaluate our proposed method on the clinical problem of detecting frames containing polyps from colonoscopy video sequences, where the training set has 13350 normal images (i.e., without polyps) and less than 100 abnormal images (i.e., with polyps). The results of our proposed model on this data set reveal a state-of-the-art detection result, while the performance based on different number of anomaly samples is relatively stable after approximately 40 abnormal training images.