mlsanityData to 7 Oct 2026

Rethinking Polyp Segmentation from an Out-of-Distribution Perspective

arXiv 2306.07792 ↗First posted 13 Jun 2023eess.IV cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Unlike existing fully-supervised approaches, we rethink colorectal polyp segmentation from an out-of-distribution perspective with a simple but effective self-supervised learning approach. We leverage the ability of masked autoencoders -- self-supervised vision transformers trained on a reconstruction task -- to learn in-distribution representations; here, the distribution of healthy colon images. We then perform out-of-distribution reconstruction and inference, with feature space standardisation to align the latent distribution of the diverse abnormal samples with the statistics of the healthy samples. We generate per-pixel anomaly scores for each image by calculating the difference between the input and reconstructed images and use this signal for out-of-distribution (ie, polyp) segmentation. Experimental results on six benchmarks show that our model has excellent segmentation performance and generalises across datasets. Our code is publicly available at https://github.com/GewelsJI/Polyp-OOD.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 30 of its 55 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

30 of 55 references.

References · 30

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2023Segment Anythingcited by 8,158
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2019Kvasir-SEG: A Segmented Polyp Datasetcited by 588
  5. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  6. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  7. 2020PraNet: Parallel Reverse Attention Network for Polyp Segmentationcited by 460
  8. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  9. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  10. 2022MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesiscited by 222
  11. 2019ResUNet++: An Advanced Architecture for Medical Image Segmentationcited by 211
  12. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 105
18 more
  1. 2023Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Groupingcited by 92
  2. 2022Video Polyp Segmentation: A Deep Learning Perspectivecited by 81
  3. 2021Progressively Normalized Self-Attention Network for Video Polyp Segmentationcited by 75
  4. 2023SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anythingcited by 75
  5. 2018Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distancecited by 74
  6. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  7. 2020Unsupervised Lesion Detection via Image Restoration with a Normative Priorcited by 65
  8. 2021UACANet: Uncertainty Augmented Context Attention for Polyp Segmentationcited by 61
  9. 2023Can SAM Segment Polyps?cited by 59
  10. 2023Advances in Deep Concealed Scene Understandingcited by 47
  11. 2021Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Imagescited by 45
  12. 2022Expanding Low-Density Latent Regions for Open-Set Object Detectioncited by 38
  13. 2021Focus U-Net: A novel dual attention-gated CNN for polyp segmentation during colonoscopycited by 20
  14. 2022Unsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked Autoencodercited by 15
  15. 2019Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentationcited by 14
  16. 2023Self-Supervised Correction Learning for Semi-Supervised Biomedical Image Segmentationcited by 7
  17. 2020Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentationcited by 6
  18. 2022Towards Automated Polyp Segmentation Using Weakly- and Semi-Supervised Learning and Deformable Transformerscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024Frontiers in Intelligent Colonoscopycited by 13
  2. 2024LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusioncited by 12
  3. 2025Enhancing kelp forest detection in remote sensing images using crowdsourced labels with Mixed Vision Transformers and ConvNeXt segmentation modelscited by 2
  4. 2026Rethinking Camouflage Image Generation towards a Training-Free Paradigmcited by 0