A Qualitative Review of GenAI-Based Methods for Data Generation and Augmentation in Industrial Computer Vision Applications

2026-06-12

AI Summary

This study addresses the “chicken-and-egg” dilemma in industrial computer vision—characterized by scarce high-quality annotated data and insufficient model trustworthiness—where conventional active learning often undermines user confidence. The work provides a systematic review of generative artificial intelligence (GenAI) approaches for data generation and augmentation in industrial visual classification tasks, with a novel focus on semantic context and object feature domain adaptation specific to industrial settings. It identifies a critical challenge: the mismatch between source and target domains. Through qualitative analysis of cutting-edge techniques such as diffusion models and large language model–guided image generation, the study reveals that while GenAI holds promise for automatically expanding training data, it frequently suffers from a domain misalignment between natural language descriptions and the intrinsic characteristics of industrial objects, thereby limiting real-world deployment efficacy and offering new insights toward building trustworthy industrial AI systems.

Abstract

AI-driven computer vision applications require a profound database to ensure predictable behaviors and performance. Such predictable behaviors are especially important for industrial applications in gaining trust from users. However, such a database is not readily available in industrial applications, and its acquisition is not trivial either. Active learning methods can be applied to ramp up data within a project deployment to iteratively increase the database, and thus the application predictability. Unfortunately, we observe that this often leads to a loss of user trust in the application, which is difficult to regain once lost. This leads to a "chicken-and-egg" dilemma in which neither the database nor the application is developed. In this work, we review state-of-the-art methods and approaches to further boost the database the initial active data ramp-up phase. Here, we focus on recent advancements in GenAI-based data generation and augmentation methods and review their adaptability on an industrial computer vision classification use case. Although we observe a potential for automatic data ramp-up, we also see a domain miss match in between the source (training environment) and target (industrial use-case) - regarding context defined in natural language and object characteristics.

Problem

• industrial computer vision
• data scarcity
• user trust
• domain mismatch
• database initialization

Innovation

• Generative AI
• Data Augmentation
• Industrial Computer Vision
• Domain Mismatch
• Active Learning