Controllable Image Synthesis of Industrial Data Using Stable Diffusion

• URL: http://arxiv.org/abs/2401.03152v1
• Date: Sat, 6 Jan 2024 08:09:24 GMT
• Title: Controllable Image Synthesis of Industrial Data Using Stable Diffusion
• Authors: Gabriele Valvano, Antonino Agostino, Giovanni De Magistris, Antonino Graziano, Giacomo Veneri
• Abstract summary: We propose a new approach for reusing general-purpose pre-trained generative models on industrial data. First, we let the model learn the new concept, entailing the novel data distribution. Then, we force it to learn to condition the generative process, producing industrial images that satisfy well-defined topological characteristics.
• Score: 2.021800129069459
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training supervised deep neural networks that perform defect detection and segmentation requires large-scale fully-annotated datasets, which can be hard or even impossible to obtain in industrial environments. Generative AI offers opportunities to enlarge small industrial datasets artificially, thus enabling the usage of state-of-the-art supervised approaches in the industry. Unfortunately, also good generative models need a lot of data to train, while industrial datasets are often tiny. Here, we propose a new approach for reusing general-purpose pre-trained generative models on industrial data, ultimately allowing the generation of self-labelled defective images. First, we let the model learn the new concept, entailing the novel data distribution. Then, we force it to learn to condition the generative process, producing industrial images that satisfy well-defined topological characteristics and show defects with a given geometry and location. To highlight the advantage of our approach, we use the synthetic dataset to optimise a crack segmentor for a real industrial use case. When the available data is small, we observe considerable performance increase under several metrics, showing the method's potential in production environments.

Related papers

• Fractals as Pre-training Datasets for Anomaly Detection and Localization [0.0]
  Anomaly detection is crucial in large-scale industrial manufacturing as it helps detect and localise defective parts. Pre-training feature extractors on large-scale datasets is a popular approach for this task. We evaluate the performance of eight state-of-the-art methods pre-trained using dynamically generated fractal images.
  arXiv  Detail & Related papers  (2024-05-11T10:35:42Z)
• IPAD: Industrial Process Anomaly Detection Dataset [71.39058003212614]
  Video anomaly detection (VAD) is a challenging task aiming to recognize anomalies in video frames. We propose a new dataset, IPAD, specifically designed for VAD in industrial scenarios. This dataset covers 16 different industrial devices and contains over 6 hours of both synthetic and real-world video footage.
  arXiv  Detail & Related papers  (2024-04-23T13:38:01Z)
• Investigation of the Impact of Synthetic Training Data in the Industrial Application of Terminal Strip Object Detection [4.327763441385371]
  In this paper, we investigate the sim-to-real generalization performance of standard object detectors on the complex industrial application of terminal strip object detection. We manually annotated 300 real images of terminal strips for the evaluation. The results show the cruciality of the objects of interest to have the same scale in either domain.
  arXiv  Detail & Related papers  (2024-03-06T18:33:27Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• Synthetic data, real errors: how (not) to publish and use synthetic data [86.65594304109567]
  We show how the generative process affects the downstream ML task. We introduce Deep Generative Ensemble (DGE) to approximate the posterior distribution over the generative process model parameters.
  arXiv  Detail & Related papers  (2023-05-16T07:30:29Z)
• Synthetic Data for Object Classification in Industrial Applications [53.180678723280145]
  In object classification, capturing a large number of images per object and in different conditions is not always possible. This work explores the creation of artificial images using a game engine to cope with limited data in the training dataset.
  arXiv  Detail & Related papers  (2022-12-09T11:43:04Z)
• Deep Learning based pipeline for anomaly detection and quality enhancement in industrial binder jetting processes [68.8204255655161]
  Anomaly detection describes methods of finding abnormal states, instances or data points that differ from a normal value space. This paper contributes to a data-centric way of approaching artificial intelligence in industrial production.
  arXiv  Detail & Related papers  (2022-09-21T08:14:34Z)
• Contrastive Model Inversion for Data-Free Knowledge Distillation [60.08025054715192]
  We propose Contrastive Model Inversion, where the data diversity is explicitly modeled as an optimizable objective. Our main observation is that, under the constraint of the same amount of data, higher data diversity usually indicates stronger instance discrimination. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that CMI achieves significantly superior performance when the generated data are used for knowledge distillation.
  arXiv  Detail & Related papers  (2021-05-18T15:13:00Z)
• Segmenting Unseen Industrial Components in a Heavy Clutter Using RGB-D Fusion and Synthetic Data [0.4724825031148411]
  Industrial components are texture-less, reflective, and often found in cluttered and unstructured environments. We present a synthetic data generation pipeline that randomizes textures via domain randomization to focus on the shape information. We also propose an RGB-D Fusion Mask R-CNN with a confidence map estimator, which exploits reliable depth information in multiple feature levels.
  arXiv  Detail & Related papers  (2020-02-10T02:33:21Z)
• Forecasting Industrial Aging Processes with Machine Learning Methods [0.0]
  We evaluate a wider range of data-driven models, comparing some traditional stateless models to more complex recurrent neural networks. Our results show that recurrent models produce near perfect predictions when trained on larger datasets.
  arXiv  Detail & Related papers  (2020-02-05T13:06:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.