RaPP: Novelty Detection with Reconstruction along Projection Pathway
We propose RaPP, a new methodology for novelty detection by utilizing hidden space activation values obtained from a deep autoencoder. Precisely, RaPP compares input and its autoencoder reconstruction not only in the input space but also in the hidden spaces. We show that if we feed a reconstructed input to the same autoencoder again, its activated values in a hidden space are equivalent to the corresponding reconstruction in that hidden space given the original input. In order to aggregate the hidden space activation values, we propose two metrics, which enhance the novelty detection performance. Through extensive experiments using diverse datasets, we validate that RaPP improves novelty detection performances of autoencoder-based approaches. Besides, we show that RaPP outperforms recent novelty detection methods evaluated on popular benchmarks.
Code (1)
Tasks
Anomaly DetectionNovelty DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models
Novelty detection is a fundamental task of machine learning which aims to detect abnormal ($\textit{i.e.}$ out-of-distribution (OOD)) samples. Since diffusion models have recently emerged as the de facto standard generat…
Novelty DetectionPerceptual DistanceOAAE: Adversarial Autoencoders for Novelty Detection in Multi-modal Normality Case via Orthogonalized Latent Space
Novelty detection using deep generative models such as autoencoder, generative adversarial networks mostly takes image reconstruction error as novelty score function. However, image data, high dimensional as it is, conta…
Image ReconstructionNovelty DetectionDeep Back Projection for Sparse-View CT Reconstruction
Filtered back projection (FBP) is a classical method for image reconstruction from sinogram CT data. FBP is computationally efficient but produces lower quality reconstructions than more sophisticated iterative methods, …
CT ReconstructionImage ReconstructionPrimal: A Unified Deterministic Framework for Quasi-Orthogonal Hashing and Manifold Learning
We present Primal, a deterministic feature mapping framework that harnesses the number-theoretic independence of prime square roots to construct robust, tunable vector representations. Diverging from standard stochastic …
Compressive SensingSelf-supervised phase unwrapping in fringe projection profilometry
Fast-speed and high-accuracy three-dimensional (3D) shape measurement has been the goal all along in fringe projection profilometry (FPP). The dual-frequency temporal phase unwrapping method (DF-TPU) is one of the promin…