paper-with-me

Papers

Inpainting Transformer for Anomaly Detection

2021-04-28 · Jonathan Pirnay, Keng Chai

Anomaly detection in computer vision is the task of identifying images which deviate from a set of normal images. A common approach is to train deep convolutional autoencoders to inpaint covered parts of an image and compare the output with the original image. By training on anomaly-free samples only, the model is assumed to not being able to reconstruct anomalous regions properly. For anomaly detection by inpainting we suggest it to be beneficial to incorporate information from potentially distant regions. In particular we pose anomaly detection as a patch-inpainting problem and propose to solve it with a purely self-attention based approach discarding convolutions. The proposed Inpainting Transformer (InTra) is trained to inpaint covered patches in a large sequence of image patches, thereby integrating information across large regions of the input image. When training from scratch, in comparison to other methods not using extra training data, InTra achieves results on par with the current state-of-the-art on the MVTec AD dataset for detection and surpassing them on segmentation.

📄 PDF Abstract BibTeX arXiv:2104.13897

Code (2)

jhy12/inpainting-transformer pytorch
uzl/inpainting-transformer pytorch

Tasks

Anomaly Detection

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

MAEDAY: MAE for few and zero shot AnomalY-Detection

2022-11-25 · Eli Schwartz, Assaf Arbelle, Leonid Karlinsky, Sivan Harary 외

We propose using Masked Auto-Encoder (MAE), a transformer model self-supervisedly trained on image inpainting, for anomaly detection (AD). Assuming anomalous regions are harder to reconstruct compared with normal regions…

Anomaly DetectionImage InpaintingImage Reconstructionobject-detection+2

Iterative Image Inpainting with Structural Similarity Mask for Anomaly Detection

2021-01-01 · Hitoshi Nakanishi, Masahiro Suzuki, Yutaka Matsuo

Autoencoders have emerged as popular methods for unsupervised anomaly detection. Autoencoders trained on the normal data are expected to reconstruct only the normal features, allowing anomaly detection by thresholding re…

Anomaly DetectionImage InpaintingUnsupervised Anomaly Detection

Reconstruction by Inpainting for Visual Anomaly Detection

2020-10-17 · Vitjan Zavrtanik, Matej Kristan, Danijel Skočaj

Visual anomaly detection addresses the problem of classification or localization of regions in an image that deviate from their normal appearance. A popular approach trains an auto-encoder on anomaly-free images and perf…

Anomaly Detection

AnomalySD: Few-Shot Multi-Class Anomaly Detection with Stable Diffusion Model

2024-08-04 · Zhenyu Yan, Qingqing Fang, Wenxi Lv, Qinliang Su

Anomaly detection is a critical task in industrial manufacturing, aiming to identify defective parts of products. Most industrial anomaly detection methods assume the availability of sufficient normal data for training. …

Anomaly ClassificationAnomaly DetectionMulti-class Anomaly Detection

UniADC: A Unified Framework for Anomaly Detection and Classification

2025-11-10 · Ximiao Zhang, Min Xu, Zheng Zhang, Yap-Peng Tan 외 arxiv

In this paper, we introduce a novel task termed unified anomaly detection and classification, which aims to simultaneously detect anomalous regions in images and identify their specific categories. Existing methods typic…

Anomaly Detection