mlsanityData to 7 Oct 2026

Image Outlier Detection Without Training using RANSAC

arXiv 2307.12301 ↗First posted 23 Jul 2023cs.CV cs.IR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Image outlier detection (OD) is an essential tool to ensure the quality of images used in computer vision tasks. Existing algorithms often involve training a model to represent the inlier distribution, and outliers are determined by some deviation measure. Although existing methods proved effective when trained on strictly inlier samples, their performance remains questionable when undesired outliers are included during training. As a result of this limitation, it is necessary to carefully examine the data when developing OD models for new domains. In this work, we present a novel image OD algorithm called RANSAC-NN that eliminates the need of data examination and model training altogether. Unlike existing approaches, RANSAC-NN can be directly applied on datasets containing outliers by sampling and comparing subsets of the data. Our algorithm maintains favorable performance compared to existing methods on a range of benchmarks. Furthermore, we show that RANSAC-NN can enhance the robustness of existing methods by incorporating our algorithm as part of the data preparation process.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 55 references that are in the map. First posted on arXiv 23 Jul 2023.

Builds on

28 of 55 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017Billion-scale similarity search with GPUscited by 2,477
  4. 2019Searching for MobileNetV3cited by 1,984
  5. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  6. 2021ImageNet-21K Pretraining for the Massescited by 607
  7. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  8. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  9. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  10. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  11. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  12. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
16 more
  1. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  2. 2023A Cookbook of Self-Supervised Learningcited by 248
  3. 2019PyOD: A Python Toolbox for Scalable Outlier Detectioncited by 221
  4. 2020Classification-Based Anomaly Detection for General Datacited by 210
  5. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
  6. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  7. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
  8. 2022Deep Isolation Forest for Anomaly Detectioncited by 90
  9. 2018Learning Deep Features for One-Class Classificationcited by 76
  10. 2018Generative Adversarial Active Learning for Unsupervised Outlier Detectioncited by 65
  11. 2021LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networkscited by 42
  12. 2019One-Class Convolutional Neural Networkcited by 37
  13. 2020Puzzle-AE: Novelty Detection in Images through Solving Puzzlescited by 23
  14. 2022Back to the Basics: Revisiting Out-of-Distribution Detection Baselinescited by 16
  15. 2021Visual Anomaly Detection for Images: A Surveycited by 11
  16. 2020Self-Supervised Representation Learning for Visual Anomaly Detectioncited by 5

Built on by

Not cited yet.