用少量无标签金属显微图像训练，实现更优的材料图像分割效果。
MatSSL: Robust Self-Supervised Representation Learning for Metallographic Image Segmentation
- 在骨干网络每阶段使用门控特征融合，整合多层级特征表示。
- 在MetalDAM数据集上达到69.13% mIoU，优于ImageNet预训练模型。
- 仅需小规模无标签数据即可适配金属图像领域，适合资源有限场景。
MatSSL是一种简化的自监督学习架构，通过在骨干网络每个阶段引入门控特征融合，有效整合多层级表征。当前金属材料显微图像分析依赖监督方法，需为每新数据集重新训练，且在少量标注样本下表现不稳定。尽管自监督学习可利用无标签数据，但多数方法仍需大规模数据才能生效。MatSSL先在小规模无标签数据上进行自监督预训练，再在多个基准数据集上微调。结果在MetalDAM数据集上达69.13% mIoU，优于ImageNet预训练编码器的66.73%；在环境屏障涂层（EBC）数据集上平均mIoU提升近40%，显著优于MicroNet预训练模型。表明MatSSL仅用少量无标签数据即可有效适应金属学领域，同时保留自然图像大模型中学习到的丰富可迁移特征。
原文摘要 · Abstract (English)
MatSSL is a streamlined self-supervised learning (SSL) architecture that employs Gated Feature Fusion at each stage of the backbone to integrate multi-level representations effectively. Current micrograph analysis of metallic materials relies on supervised methods, which require retraining for each new dataset and often perform inconsistently with only a few labeled samples. While SSL offers a promising alternative by leveraging unlabeled data, most existing methods still depend on large-scale datasets to be effective. MatSSL is designed to overcome this limitation. We first perform self-supervised pretraining on a small-scale, unlabeled dataset and then fine-tune the model on multiple benchmark datasets. The resulting segmentation models achieve 69.13% mIoU on MetalDAM, outperforming the 66.73% achieved by an ImageNet-pretrained encoder, and delivers consistently up to nearly 40% improvement in average mIoU on the Environmental Barrier Coating benchmark dataset (EBC) compared to models pretrained with MicroNet. This suggests that MatSSL enables effective adaptation to the metallographic domain using only a small amount of unlabeled data, while preserving the rich and transferable features learned from large-scale pretraining on natural images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。