SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.17316 · 2023

Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
EnVision-Research/Defect_Spectrum canonical 4 of 5
FunctionStatusWhere it lives
get_first_five_images Ran EnVision-Research/Defect_Spectrum/dataset/image_datasets.py
code served (permissive licence) · get_code("40369adbc7a4787e")
is_image_file Ran EnVision-Research/Defect_Spectrum/dataset/base_dataset.py
code served (permissive licence) · get_code("6f527bbe13c81b60")
make_dataset Ran EnVision-Research/Defect_Spectrum/dataset/base_dataset.py
code served (permissive licence) · get_code("35db53e6de24ca77")
normal_kl Ran EnVision-Research/Defect_Spectrum/models/distributions.py
code served (permissive licence) · get_code("17eb0a31c91b671c")
extract Not yet run EnVision-Research/Defect_Spectrum/diffusion/base_diffusion.py
code served (permissive licence) · get_code("07591fa9422585e7")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.17316")
get_code_for_paper("2310.17316")
have("2310.17316")

Connect an agent — have() is free.