Saved in:
Bibliographic Details
Main Authors: Yang, Shuai, Chen, Zhifei, Chen, Pengguang, Fang, Xi, Liang, Yixun, Liu, Shu, Chen, Yingcong
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.17316
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917727953747968
author Yang, Shuai
Chen, Zhifei
Chen, Pengguang
Fang, Xi
Liang, Yixun
Liu, Shu
Chen, Yingcong
author_facet Yang, Shuai
Chen, Zhifei
Chen, Pengguang
Fang, Xi
Liang, Yixun
Liu, Shu
Chen, Yingcong
contents Defect inspection is paramount within the closed-loop manufacturing system. However, existing datasets for defect inspection often lack precision and semantic granularity required for practical applications. In this paper, we introduce the Defect Spectrum, a comprehensive benchmark that offers precise, semantic-abundant, and large-scale annotations for a wide range of industrial defects. Building on four key industrial benchmarks, our dataset refines existing annotations and introduces rich semantic details, distinguishing multiple defect types within a single image. Furthermore, we introduce Defect-Gen, a two-stage diffusion-based generator designed to create high-quality and diverse defective images, even when working with limited datasets. The synthetic images generated by Defect-Gen significantly enhance the efficacy of defect inspection models. Overall, The Defect Spectrum dataset demonstrates its potential in defect inspection research, offering a solid platform for testing and refining advanced models.
format Preprint
id arxiv_https___arxiv_org_abs_2310_17316
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics
Yang, Shuai
Chen, Zhifei
Chen, Pengguang
Fang, Xi
Liang, Yixun
Liu, Shu
Chen, Yingcong
Computer Vision and Pattern Recognition
Defect inspection is paramount within the closed-loop manufacturing system. However, existing datasets for defect inspection often lack precision and semantic granularity required for practical applications. In this paper, we introduce the Defect Spectrum, a comprehensive benchmark that offers precise, semantic-abundant, and large-scale annotations for a wide range of industrial defects. Building on four key industrial benchmarks, our dataset refines existing annotations and introduces rich semantic details, distinguishing multiple defect types within a single image. Furthermore, we introduce Defect-Gen, a two-stage diffusion-based generator designed to create high-quality and diverse defective images, even when working with limited datasets. The synthetic images generated by Defect-Gen significantly enhance the efficacy of defect inspection models. Overall, The Defect Spectrum dataset demonstrates its potential in defect inspection research, offering a solid platform for testing and refining advanced models.
title Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2310.17316