Learning Discriminative Reconstructions for Unsupervised Outlier Removal
We study the problem of automatically removing outliers from noisy data, with application for removing outlier images from an image collection. We address this problem by utilizing the reconstruction errors of an autoencoder. We observe that when data are reconstructed from low-dimensional representations, the inliers and the outliers can be well separated according to their reconstruction errors. Based on this basic observation, we gradually inject discriminative information in the learning process of an autoencoder to make the inliers and the outliers more separable. Experiments on a variety of image datasets validate our approach.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Efficient Background Modeling Based on Sparse Representation and Outlier Iterative Removal
Background modeling is a critical component for various vision-based applications. Most traditional methods tend to be inefficient when solving large-scale problems. In this paper, we introduce sparse representation into…
Leveraging the Mahalanobis Distance to enhance Unsupervised Brain MRI Anomaly Detection
Unsupervised Anomaly Detection (UAD) methods rely on healthy data distributions to identify anomalies as outliers. In brain MRI, a common approach is reconstruction-based UAD, where generative models reconstruct healthy …
Anomaly DetectionUnsupervised Anomaly DetectionClean-GS: Semantic Mask-Guided Pruning for 3D Gaussian Splatting
3D Gaussian Splatting produces high-quality scene reconstructions but generates hundreds of thousands of spurious Gaussians (floaters) scattered throughout the environment. These artifacts obscure objects of interest and…
Model CompressionRobust Outlier Rejection for 3D Registration with Variational Bayes
Learning-based outlier (mismatched correspondence) rejection for robust 3D registration generally formulates the outlier removal as an inlier/outlier classification problem. The core for this to be successful is to learn…
Bayesian InferenceEffective End-to-end Unsupervised Outlier Detection via Inlier Priority of Discriminative Network
Despite the wide success of deep neural networks (DNN), little progress has been made on end-to-end unsupervised outlier detection (UOD) from high dimensional data like raw images. In this paper, we propose a framework n…
Outlier DetectionRepresentation LearningUnsupervised Anomaly Detection