เปรียบเทียบวิธี

	ทรานส์ฟอร์มเมอร์วิสัยทัศน์หลายรูปแบบ	วิชันทรานส์ฟอร์มเมอร์ที่ปรับละเอียด
สาขาวิชา	การเรียนรู้เชิงลึก	การเรียนรู้เชิงลึก
ตระกูล	Machine learning	Machine learning
ปีกำเนิด	2021	2020-2021
ผู้ริเริ่ม	Dosovitskiy et al. (ViT); Radford et al. (CLIP multimodal ViT)	Dosovitskiy, A. et al. (Google Brain)
ประเภท	Multimodal transformer model	Transfer learning / fine-tuning of attention-based image model
แหล่งต้นตำรับ	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).	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 2021).
ชื่อเรียกอื่น	Multimodal ViT, vision-language transformer, cross-modal vision transformer, multi-modal ViT	Fine-Tuned ViT, ViT fine-tuning, Vision Transformer transfer learning, ViT downstream adaptation
ที่เกี่ยวข้อง	5	5
สรุป	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.	Fine-Tuned Vision Transformer adapts a large pre-trained ViT model — which splits images into fixed-size patches and processes them through self-attention layers — to a new image classification or recognition task using a relatively small labeled dataset. It achieves state-of-the-art accuracy in computer vision by leveraging rich representations learned during large-scale pre-training.