LERENet: Eliminating Intra-class Differences for Metal Surface Defect Few-shot Semantic Segmentation
Not on the map. Why?
Abstract (arXiv)
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 textitIntra-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 textitSemantic Difference induced by internal factors in metal samples and the textitDistortion 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 textitSemantic 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 textitDistortion 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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 50 references that are in the map. First posted on arXiv 17 Mar 2024.
Builds on
27 of 50 references.
References · 27
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
- 2017One-Shot Learning for Semantic Segmentationcited by 337
- 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
- 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
- 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
- 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
- 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
- 2018Graph-Based Global Reasoning Networkscited by 120
15 more
- 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
- 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
- 2021Mining Latent Classes for Few-shot Segmentationcited by 69
- 2019Differentiable Meta-learning Model for Few-shot Semantic Segmentationcited by 31
- 2022Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentationcited by 28
- 2023MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentationcited by 25
- 2020Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalizationcited by 20
- 2022Self-Regularized Prototypical Network for Few-Shot Semantic Segmentationcited by 12
- 2023Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentationcited by 12
- 2021APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentationcited by 11
- 2023Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentationcited by 10
- 2021Prototype Completion for Few-Shot Learningcited by 7
- 2023Few-Shot Rotation-Invariant Aerial Image Semantic Segmentationcited by 7
- 2020Graph Fairing Convolutional Networks for Anomaly Detectioncited by 5
- 2023Few-shot Semantic Segmentation with Support-induced Graph Convolutional Networkcited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.