Compara mètodes
Revisa els mètodes seleccionats l'un al costat de l'altre; les files que difereixen es ressalten.
| Transformador de Visió Multimodal× | Classificació basada en BERT× | |
|---|---|---|
| Camp | Aprenentatge profund | Aprenentatge profund |
| Família | Machine learning | Machine learning |
| Any d'origen≠ | 2021 | 2019 |
| Autor original≠ | Dosovitskiy et al. (ViT); Radford et al. (CLIP multimodal ViT) | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language) |
| Tipus≠ | Multimodal transformer model | Pre-trained language model with fine-tuning |
| Font seminal≠ | 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. In International Conference on Learning Representations (ICLR). link ↗ | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics. DOI ↗ |
| Àlies | Multimodal ViT, vision-language transformer, cross-modal vision transformer, multi-modal ViT | BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS |
| Relacionats≠ | 5 | 4 |
| Resum≠ | Multimodal Vision Transformer (Multimodal ViT) extends the Vision Transformer architecture to jointly process and align representations from multiple modalities — typically images and text — using self-attention and cross-attention mechanisms. By learning shared or aligned embedding spaces across modalities, it enables tasks such as visual question answering, image-text retrieval, visual grounding, and image captioning. | BERT-based Classification fine-tunes Google's Bidirectional Encoder Representations from Transformers model on a labelled text dataset, replacing the generic pre-trained head with a task-specific classification layer. It exploits deep bidirectional context from hundreds of millions of pre-trained parameters to deliver state-of-the-art accuracy on short- and medium-length text classification tasks with relatively modest amounts of labelled data. |
| ScholarGateConjunt de dades ↗ |
|
|