# LERENet: Eliminating Intra-class Differences for Metal Surface Defect Few-shot Semantic Segmentation

arXiv: https://arxiv.org/abs/2403.11122 · HTML: https://mlsanity.com/paper/2403.11122/

## Key facts

- Cited by 1 papers 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 (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [Prior Guided Feature Enrichment Network for Few-Shot Segmentation](https://mlsanity.com/paper/2008.01449/) (2020)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Adaptive Prototype Learning and Allocation for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01893/) (2021)
- [SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation](https://mlsanity.com/paper/1810.09091/) (2018)
- [Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning](https://mlsanity.com/paper/1903.12290/) (2019)
- [Graph-Based Global Reasoning Networks](https://mlsanity.com/paper/1811.12814/) (2018)
- [Learning What Not to Segment: A New Perspective on Few-Shot Segmentation](https://mlsanity.com/paper/2203.07615/) (2022)
- [Hierarchical Dense Correlation Distillation for Few-Shot Segmentation](https://mlsanity.com/paper/2303.14652/) (2023)
- [Mining Latent Classes for Few-shot Segmentation](https://mlsanity.com/paper/2103.15402/) (2021)
- [Differentiable Meta-learning Model for Few-shot Semantic Segmentation](https://mlsanity.com/paper/1911.10371/) (2019)
- [Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation](https://mlsanity.com/paper/2204.09903/) (2022)
- [MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2305.13864/) (2023)
- [Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization](https://mlsanity.com/paper/2003.12296/) (2020)
- [Self-Regularized Prototypical Network for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2210.16829/) (2022)
- [Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation](https://mlsanity.com/paper/2305.06568/) (2023)
- [APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2111.12263/) (2021)
- [Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2305.07283/) (2023)
- [Prototype Completion for Few-Shot Learning](https://mlsanity.com/paper/2108.05010/) (2021)
- [Few-Shot Rotation-Invariant Aerial Image Semantic Segmentation](https://mlsanity.com/paper/2306.11734/) (2023)
- [Graph Fairing Convolutional Networks for Anomaly Detection](https://mlsanity.com/paper/2010.10274/) (2020)
- [Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network](https://mlsanity.com/paper/2301.03194/) (2023)

## Built on by (most cited first, 1 of 1)

- [UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting](https://mlsanity.com/paper/2604.02905/) (2026)

## 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.