FSC-20 dataset
We constructed a large-scale few-shot classification dataset named FSC-20(few-shot classification contains 20 types of strip steel surface defects). This dataset was collected from the three datasets the NEU-CLS, the X-SDD, and the GC10-DET, with a total of 20 categories. Specifically, it includes 10 types of cold-rolled defects (all from GC10-DET) and 10 types of hot-rolled defects (6 types from NEU-CLS and the other 4 types from X-SDD).
FaNet
We propose a feature-aware network (FaNet) for a few shot defect classification, which can effectively distinguish new classes with a small number of labeled samples.
Download the dataset and code
The dataset and code are available at:https://pan.baidu.com/s/1k_ClBD9DSKUxCtcQU3qM3Q?pwd=3ewk
Paper
https://www.sciencedirect.com/science/article/abs/pii/S0263224123000106
2023-FaNet Feature-aware network for few shot classification of strip steel surface defects.pdf
Citation
Zhao W, Song K, Wang Y, et al. FaNet: Feature-aware Network for Few Shot Classification of Strip Steel Surface Defects[J]. Measurement, 2023: 112446.
Related work of few-shot classification for surface defects
[1] MSD-Cls dataset & GTnet The dataset and code are available at:https://github.com/successhaha/GTnet
Few-shot surface defect segmentation
[1] TGRNet： Triplet-graph reasoning network for few-shot metal generic surface defect segmentation The dataset and code are available at:https://pan.baidu.com/s/1dEai3yXrFOsuWcQ5mkE7_A?pwd=qzo6
[2] FSSD-12 dataset & CPANet The dataset and code are available at:https://github.com/VDT-2048/CPANet