Chuni Liu
YOU?
Author Swipe
View article: Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset
Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset Open
The pretraining-finetuning paradigm is a crucial strategy in metallic surface defect detection for mitigating the challenges posed by data scarcity. However, its implementation presents a critical dilemma. Pretraining on natural image data…
View article: A Few-Shot Steel Surface Defect Generation Method Based on Diffusion Models
A Few-Shot Steel Surface Defect Generation Method Based on Diffusion Models Open
Few-shot steel surface defect generation remains challenging due to the limited availability of training samples and the complex visual characteristics of industrial defects. Traditional data augmentation techniques often fail to capture t…
View article: Enhancing Boundary Segmentation for Topological Accuracy with Skeleton-based Methods
Enhancing Boundary Segmentation for Topological Accuracy with Skeleton-based Methods Open
Topological consistency plays a crucial role in the task of boundary segmentation for reticular images, such as cell membrane segmentation in neuron electron microscopic images, grain boundary segmentation in material microscopic images an…
View article: Boundary learning by using weighted propagation in convolution network
Boundary learning by using weighted propagation in convolution network Open
View article: Author Correction: Data augmentation in microscopic images for material data mining
Author Correction: Data augmentation in microscopic images for material data mining Open
An amendment to this paper has been published and can be accessed via a link at the top of the paper.
View article: Data augmentation in microscopic images for material data mining
Data augmentation in microscopic images for material data mining Open
Recent progress in material data mining has been driven by high-capacity models trained on large datasets. However, collecting experimental data (real data) has been extremely costly owing to the amount of human effort and expertise requir…
View article: WPU-Net:Boundary learning by using weighted propagation in convolution network
WPU-Net:Boundary learning by using weighted propagation in convolution network Open
Deep learning has driven a great progress in natural and biological image processing. However, in material science and engineering, there are often some flaws and indistinctions in material microscopic images induced from complex sample pr…
View article: Style transfer based data augmentation in material microscopic image processing.
Style transfer based data augmentation in material microscopic image processing. Open
Recently progress in material microscopic image semantic segmentation has been driven by high-capacity models trained on large datasets. However, collecting microscopic images with pixel-level labels has been extremely costly due to the am…
View article: A fast algorithm for material image sequential stitching
A fast algorithm for material image sequential stitching Open