LERENet: Eliminating Intra-class Differences for Metal Surface Defect Few-shot Semantic Segmentation
CoRR(2024)
摘要
Few-shot segmentation models excel in metal defect detection due to their
rapid generalization ability to new classes and pixel-level segmentation,
rendering them ideal for addressing data scarcity issues and achieving refined
object delineation in industrial applications. Existing works neglect the
Intra-Class Differences, inherent in metal surface defect data, which
hinders the model from learning sufficient knowledge from the support set to
guide the query set segmentation. Specifically, it can be categorized into two
types: the Semantic Difference induced by internal factors in metal
samples and the Distortion Difference caused by external factors of
surroundings. To address these differences, we introduce a Local
dEscriptor based Reasoning and Excitation
Network (LERENet) to learn the two-view guidance, i.e., local
and global information from the graph and feature space, and fuse them to
segment precisely. Since the relation structure of local features embedded in
graph space will help to eliminate Semantic Difference, we employ
Multi-Prototype Reasoning (MPR) module, extracting local descriptors based
prototypes and analyzing local-view feature relevance in support-query pairs.
Besides, due to the global information that will assist in countering the
Distortion Difference in observations, we utilize Multi-Prototype
Excitation (MPE) module to capture the global-view relations in support-query
pairs. Finally, we employ an Information Fusion Module (IFM) to fuse learned
prototypes in local and global views to generate pixel-level masks. Our
comprehensive experiments on defect datasets demonstrate that it outperforms
existing benchmarks, establishing a new state-of-the-art.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要