Few-Shot Steel Plate Surface Defect Detection with Multi-Relation Aggregation and Adaptive Support Learning

As a challenging problem in industrial scenarios, few-shot steel plate surface defect detection aims to detect novel classes given only few defect samples. Most existing few-shot object detection (FSOD) methods usually cannot accurately detect the complex and diverse steel plate surface defects, esp...

Full description

Saved in:
Bibliographic Details
Published in:ISIJ International 2023/10/15, Vol.63(10), pp.1727-1737
Main Authors: Deng, Yongbiao, Song, Yonghong
Format: Article
Language:English
Subjects:
defect detection
few-shot object detection
meta-learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As a challenging problem in industrial scenarios, few-shot steel plate surface defect detection aims to detect novel classes given only few defect samples. Most existing few-shot object detection (FSOD) methods usually cannot accurately detect the complex and diverse steel plate surface defects, especially when the defects share similar appearance. To solve this problem, we propose a novel meta-learning based few-shot detection method with multi-relation aggregation and adaptive support learning strategy. Our method follows the training paradigm of dual-branch meta learning and tries to exploit the implicit relationships between query and support images. More specifically, we design a Multi-Relational Aggregation (MRA) module to aggregate query and support feature from three different perspectives: the attention relation, the depth-wise convolution relation, and the contrastive relation. MRA module is used to guide the subsequent classification and regression by mining the commonalities and differences between the query and support images in a category-independent manner. Besides, we propose an Adaptive Support Learning (ASL) module to dynamically adjust the weights of support representations in the learning process. We evaluate our method on three datasets of steel plate surface defect (F-SSD), NEU-DET, TianChi Aluminium profile surface defect (F-TCAL) and thorough experiments we demonstrated that our model outperforms existing state-of-the-art methods by a large margin on multiple settings. Our work provides a promising direction for the field of few-shot defect detection and can be generalized to other industrial scenes.
ISSN:0915-1559
1347-5460
DOI:10.2355/isijinternational.ISIJINT-2023-118