方法对比

	多语言语义分割	多语言 Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2019–2022	2019–2020
提出者	Various (building on Long et al. 2015 FCN; multilingual extensions c. 2019–2022)	Devlin et al. (mBERT); Conneau et al. (XLM-R)
类型	Pixel-wise classification with cross-lingual features	Pre-trained cross-lingual language model
开创性文献	Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In Proceedings of ECCV 2018.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, pp. 4171–4186. Association for Computational Linguistics.
别名	cross-lingual semantic segmentation, multilingual scene parsing, multilingual pixel-wise classification, ML-SegNet	multilingual LM, cross-lingual transformer, mBERT-style model, multilingual pre-trained model
相关	3	4
摘要	Multilingual semantic segmentation is a pixel-level scene parsing approach that assigns a semantic class label to every pixel in an image while incorporating cross-lingual capabilities — enabling a single model to recognise scene-text elements, annotations, or training signals drawn from multiple languages. It combines deep encoder-decoder architectures with multilingual language representations, making it applicable to documents, street signs, natural scene images, and medical imagery across diverse linguistic contexts.	A multilingual transformer is a pre-trained language model built on the transformer architecture and trained jointly on text from dozens to over one hundred languages. Models such as mBERT and XLM-RoBERTa learn shared cross-lingual representations, enabling zero-shot or few-shot transfer: a model fine-tuned on English data can often be applied directly to French, German, Arabic, or Chinese without language-specific labels.