Image Outlier Detection Without Training using RANSAC
This addresses the need for robust outlier detection in computer vision without requiring clean training data, which is incremental as it builds on existing RANSAC and outlier detection techniques.
The paper tackles the problem of image outlier detection when training data includes outliers, presenting RANSAC-NN, a method that eliminates the need for data examination and model training, and it maintains favorable performance on benchmarks.
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.