# VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON

arXiv: https://arxiv.org/abs/2306.07890 · HTML: https://mlsanity.com/paper/2306.07890/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 13 Jun 2023.

## Builds on (most cited first, 19 of 19)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [Deep Learning for Anomaly Detection: A Survey](https://mlsanity.com/paper/1901.03407/) (2019)
- [Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation](https://mlsanity.com/paper/2206.02777/) (2022)
- [VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2104.10036/) (2021)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [Segmentation-Based Deep-Learning Approach for Surface-Defect Detection](https://mlsanity.com/paper/1903.08536/) (2019)
- [ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models](https://mlsanity.com/paper/2204.08790/) (2022)
- [Mixed supervision for surface-defect detection: from weakly to fully supervised learning](https://mlsanity.com/paper/2104.06064/) (2021)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark](https://mlsanity.com/paper/2211.13523/) (2022)
- [Self-supervised Semi-supervised Learning for Data Labeling and Quality Evaluation](https://mlsanity.com/paper/2111.10932/) (2021)
- [Synthetic Defect Generation for Display Front-of-Screen Quality Inspection: A Survey](https://mlsanity.com/paper/2203.03429/) (2022)

## Built on by (most cited first, 25 of 25)

- [Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions](https://mlsanity.com/paper/2308.04152/) (2023)
- [GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2406.07487/) (2024)
- [Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics](https://mlsanity.com/paper/2310.17316/) (2023)
- [VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2409.20146/) (2024)
- [Advances in Global Solvers for 3D Vision](https://mlsanity.com/paper/2602.14662/) (2026)
- [EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO](https://mlsanity.com/paper/2507.21619/) (2025)
- [EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models](https://mlsanity.com/paper/2503.14162/) (2025)
- [VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modeling](https://mlsanity.com/paper/2412.17263/) (2024)
- [OASIS: Online Sample Selection for Continual Visual Instruction Tuning](https://mlsanity.com/paper/2506.02011/) (2025)
- [Small Object Few-shot Segmentation for Vision-based Industrial Inspection](https://mlsanity.com/paper/2407.21351/) (2024)
- [Industrial Language-Image Dataset (ILID): Adapting Vision Foundation Models for Industrial Settings](https://mlsanity.com/paper/2406.09637/) (2024)
- [Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization](https://mlsanity.com/paper/2503.22577/) (2025)
- [Synth4Seg -- Learning Defect Data Synthesis for Defect Segmentation using Bi-level Optimization](https://mlsanity.com/paper/2410.18490/) (2024)
- [Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervision](https://mlsanity.com/paper/2603.27179/) (2026)
- [Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines](https://mlsanity.com/paper/2606.07953/) (2026)
- [Attention Fusion Reverse Distillation for Multi-Lighting Image Anomaly Detection](https://mlsanity.com/paper/2406.04573/) (2024)
- [A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospects](https://mlsanity.com/paper/2507.13378/) (2025)
- [Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models](https://mlsanity.com/paper/2511.17487/) (2025)
- [FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detection](https://mlsanity.com/paper/2502.21012/) (2025)
- [Analyze-Prompt-Reason: A Collaborative Agent-Based Framework for Multi-Image Vision-Language Reasoning](https://mlsanity.com/paper/2508.00356/) (2025)
- [The Second-place Solution for CVPR VISION 23 Challenge Track 1 -- Data Effificient Defect Detection](https://mlsanity.com/paper/2306.14116/) (2023)
- [Leveraging Foundation Model Automatic Data Augmentation Strategies and Skeletal Points for Hands Action Recognition in Industrial Assembly Lines](https://mlsanity.com/paper/2403.09056/) (2024)
- [Find the Assembly Mistakes: Error Segmentation for Industrial Applications](https://mlsanity.com/paper/2408.12945/) (2024)
- [Noise Fusion-based Distillation Learning for Anomaly Detection in Complex Industrial Environments](https://mlsanity.com/paper/2506.16050/) (2025)
- [UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting](https://mlsanity.com/paper/2604.02905/) (2026)

## Abstract (arXiv)

Despite progress in vision-based inspection algorithms, real-world industrial challenges -- specifically in data availability, quality, and complex production requirements -- often remain under-addressed. We introduce the VISION Datasets, a diverse collection of 14 industrial inspection datasets, uniquely poised to meet these challenges. Unlike previous datasets, VISION brings versatility to defect detection, offering annotation masks across all splits and catering to various detection methodologies. Our datasets also feature instance-segmentation annotation, enabling precise defect identification. With a total of 18k images encompassing 44 defect types, VISION strives to mirror a wide range of real-world production scenarios. By supporting two ongoing challenge competitions on the VISION Datasets, we hope to foster further advancements in vision-based industrial inspection.