Sammenlign metoder
Gjennomgå de valgte metodene side om side; rader som avviker, er uthevet.
| BERT finjustering× | LoRA og PEFT× | Vision Transformer× | |
|---|---|---|---|
| Fagfelt | Dyp læring | Dyp læring | Dyp læring |
| Familie | Machine learning | Machine learning | Machine learning |
| Opprinnelsesår≠ | 2019 | 2022 | 2021 |
| Opphavsperson≠ | Devlin, J. et al. | Hu, E. J. et al.; Lester, B. et al. | Dosovitskiy, A. et al. |
| Type≠ | Transfer learning (fine-tuning a pre-trained transformer) | Parameter-efficient fine-tuning of large pretrained models | Transformer architecture for images (self-attention over patches) |
| Opprinnelig kilde≠ | Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL. DOI ↗ | Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR. link ↗ | Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗ |
| Alias≠ | BERT İnce Ayar (Fine-Tuning), BERT ince ayar, fine-tuning BERT, transfer learning with BERT | LoRA ve PEFT — Parametre Verimli İnce Ayar, Low-Rank Adaptation, parameter-efficient fine-tuning, prefix tuning | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images |
| Relaterte | 5 | 5 | 5 |
| Sammendrag≠ | BERT fine-tuning, building on the BERT model introduced by Devlin and colleagues in 2019, re-trains a pre-trained BERT model on a small labelled dataset for a target task such as classification, named-entity recognition, or question answering. Through transfer learning it reaches high performance even with relatively little task-specific data. | LoRA (Low-Rank Adaptation), introduced by Hu et al. in 2022, and the broader family of parameter-efficient fine-tuning (PEFT) methods adapt large pretrained language models to new tasks by training only a small number of extra parameters instead of every weight in the model. This makes fine-tuning possible with far less GPU memory and compute while leaving the original model largely untouched. | The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs). |
| ScholarGateDatasett ↗ |
|
|
|