paper-with-me

Papers

Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

2021-10-06 · Marco Rudolph, Tom Wehrbein, Bodo Rosenhahn, Bastian Wandt

In industrial manufacturing processes, errors frequently occur at unpredictable times and in unknown manifestations. We tackle the problem of automatic defect detection without requiring any image samples of defective parts. Recent works model the distribution of defect-free image data, using either strong statistical priors or overly simplified data representations. In contrast, our approach handles fine-grained representations incorporating the global and local image context while flexibly estimating the density. To this end, we propose a novel fully convolutional cross-scale normalizing flow (CS-Flow) that jointly processes multiple feature maps of different scales. Using normalizing flows to assign meaningful likelihoods to input samples allows for efficient defect detection on image-level. Moreover, due to the preserved spatial arrangement the latent space of the normalizing flow is interpretable which enables to localize defective regions in the image. Our work sets a new state-of-the-art in image-level defect detection on the benchmark datasets Magnetic Tile Defects and MVTec AD showing a 100% AUROC on 4 out of 15 classes.

📄 PDF Abstract BibTeX arXiv:2110.02855

Code (1)

marco-rudolph/cs-flow 공식 구현 pytorch

Tasks

Anomaly DetectionDefect DetectionUnsupervised Anomaly Detection

Methods 이 논문이 사용한 방법론

Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

Developing Synthesis Flows Without Human Knowledge

2018-04-16 · Cunxi Yu, Houping Xiao, Giovanni De Micheli

Design flows are the explicit combinations of design transformations, primarily involved in synthesis, placement and routing processes, to accomplish the design of Integrated Circuits (ICs) and System-on-Chip (SoC). Most…

Land Cover Classification from Remote Sensing Images Based on Multi-Scale Fully Convolutional Network

2020-08-01 · Rui Li, Shunyi Zheng, Chenxi Duan, Ce Zhang

In this paper, a Multi-Scale Fully Convolutional Network (MSFCN) with multi-scale convolutional kernel is proposed to exploit discriminative representations from two-dimensional (2D) satellite images.

General ClassificationLand Cover Classification

HFNO: an interpretable data-driven decomposition strategy for turbulent flows

2025-11-03 · Marco Cayuela, Vincent Le Chenadec, Peter Schmid, Taraneh Sayadi arxiv

Fourier Neural Operators (FNOs) have demonstrated exceptional accuracy in mapping functional spaces by leveraging Fourier transforms to establish a connection with underlying physical principles. However, their opaque in…

Convolutional L2LFlows: Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows

2024-05-30 · Thorsten Buss, Frank Gaede, Gregor Kasieczka, Claudius Krause 외

In the quest to build generative surrogate models as computationally efficient alternatives to rule-based simulations, the quality of the generated samples remains a crucial frontier. So far, normalizing flows have been …

Modeling Spatial Nonstationarity via Deformable Convolutions for Deep Traffic Flow Prediction

2021-01-08 · Wei Zeng, Chengqiao Lin, Kang Liu, Juncong Lin 외

Deep neural networks are being increasingly used for short-term traffic flow prediction, which can be generally categorized as convolutional (CNNs) or graph neural networks (GNNs). CNNs are preferable for region-wise tra…

PredictionTraffic Prediction