paper-with-me

Papers

RaPP: Novelty Detection with Reconstruction along Projection Pathway

2020-05-01 · ICLR 2020 1 · Ki Hyun Kim, Sangwoo Shim, Yongsub Lim, Jongseob Jeon, Jeongwoo Choi, Byungchan Kim, Andre S. Yoon

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.

📄 PDF Abstract BibTeX

Code (1)

Aiden-Jeon/RaPP pytorch

Tasks

Anomaly DetectionNovelty Detection

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models

2023-12-05 · NeurIPS 2023 11 · Sungik Choi, Hankook Lee, Honglak Lee, Moontae Lee

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 Distance

OAAE: Adversarial Autoencoders for Novelty Detection in Multi-modal Normality Case via Orthogonalized Latent Space

2021-01-07 · Sungkwon An, Jeonghoon Kim, Myungjoo Kang, Shahbaz Razaei 외

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 Detection

Deep Back Projection for Sparse-View CT Reconstruction

2018-07-06 · Dong Hye Ye, Gregery T. Buzzard, Max Ruby, Charles A. Bouman

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 Reconstruction

Primal: A Unified Deterministic Framework for Quasi-Orthogonal Hashing and Manifold Learning

2025-11-25 · Vladimer Khasia arxiv

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 Sensing

Self-supervised phase unwrapping in fringe projection profilometry

2023-02-13 · Xiaomin Gao, Wanzhong Song, Chunqian Tan, Junzhe Lei

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…