Defect Image Sample Generation With Diffusion Prior for Steel Surface Defect Recognition
The task of steel surface defect recognition is an industrial problem with great industry values. The data insufficiency is the major challenge in training a robust defect recognition network. Existing methods have investigated to enlarge the dataset by generating samples with generative models. However, their generation quality is still limited by the insufficiency of defect image samples. To this end, we propose Stable Surface Defect Generation (StableSDG), which transfers the vast generation distribution embedded in Stable Diffusion model for steel surface defect image generation. To tackle with the distinctive distribution gap between steel surface images and generated images of the diffusion model, we propose two processes. First, we align the distribution by adapting parameters of the diffusion model, adopted both in the token embedding space and network parameter space. Besides, in the generation process, we propose image-oriented generation rather than from pure Gaussian noises. We conduct extensive experiments on steel surface defect dataset, demonstrating state-of-the-art performance on generating high-quality samples and training recognition models, and both designed processes are significant for the performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection
Developing effective visual inspection models remains challenging due to the scarcity of defect data. While image generation models have been used to synthesize defect images, producing highly realistic defects remains d…
Image GenerationKnowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Method
Substation meters play a critical role in monitoring and ensuring the stable operation of power grids, yet their detection of cracks and other physical defects is often hampered by a severe scarcity of annotated samples.…
Image GenerationA Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online Adaptation
Effectively addressing the challenge of industrial Anomaly Detection (AD) necessitates an ample supply of defective samples, a constraint often hindered by their scarcity in industrial contexts. This paper introduces a n…
Anomaly DetectionDecoderImage GenerationDefFiller: Mask-Conditioned Diffusion for Salient Steel Surface Defect Generation
Current saliency-based defect detection methods show promise in industrial settings, but the unpredictability of defects in steel production environments complicates dataset creation, hampering model performance. Existin…
Data AugmentationDefect DetectionScale Where It Matters: Training-Free Localized Scaling for Diffusion Models
Diffusion models have become the dominant paradigm in text-to-image generation, and test-time scaling (TTS) improves sample quality by allocating additional computation at inference. Existing TTS methods, however, resamp…
Text-to-Image Generation