Sammenlign metoder
Gjennomgå de valgte metodene side om side; rader som avviker, er uthevet.
| Multilingual vision transformer× | Flerspråklig RoBERTa-basert klassifisering× | |
|---|---|---|
| Fagfelt | Dyp læring | Dyp læring |
| Familie | Machine learning | Machine learning |
| Opprinnelsesår≠ | 2021–2023 | 2020 |
| Opphavsperson≠ | Dosovitskiy et al. (ViT base); multilingual extension by multiple groups (2021–2023) | Conneau, A. et al. (Facebook AI Research) |
| Type≠ | Transformer-based vision model with multilingual capabilities | Pretrained multilingual transformer fine-tuned for classification |
| Opprinnelig kilde≠ | Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR 2021). link ↗ | Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzman, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2020). Unsupervised Cross-lingual Representation Learning at Scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), pp. 8440–8451. DOI ↗ |
| Alias | Multilingual ViT, Cross-lingual Vision Transformer, Multilingual Visual Transformer, ML-ViT | XLM-RoBERTa classification, mRoBERTa, cross-lingual RoBERTa classifier, multilingual transformer classification |
| Relaterte | 4 | 4 |
| Sammendrag≠ | Multilingual Vision Transformer (Multilingual ViT) extends the Vision Transformer architecture to operate across multiple languages, enabling image understanding and image-text reasoning in multilingual or cross-lingual settings. It combines patch-based image encoding with multilingual text representations, allowing a single model to serve diverse linguistic communities for tasks such as image captioning, visual question answering, and cross-lingual image retrieval. | Multilingual RoBERTa-based classification uses XLM-RoBERTa — a transformer pretrained on 100+ languages via masked language modeling — and fine-tunes it on labeled text to assign categories across multiple languages. By sharing a single model across languages, it enables robust cross-lingual and zero-shot text classification without needing separate per-language classifiers. |
| ScholarGateDatasett ↗ |
|
|