Methoden vergleichen

	BERT-Feinabstimmung	GPT-Feinabstimmung	Vision Transformer
Fachgebiet	Deep Learning	Deep Learning	Deep Learning
Familie	Machine learning	Machine learning	Machine learning
Entstehungsjahr	2019	2019	2021
Urheber	Devlin, J. et al.	Radford, A. et al. (OpenAI)	Dosovitskiy, A. et al.
Typ	Transfer learning (fine-tuning a pre-trained transformer)	Fine-tuning of pretrained autoregressive language models	Transformer architecture for images (self-attention over patches)
Wegweisende Quelle	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL.	Radford, A., Wu, J., Child, R., Luan, D., Amodei, D. & Sutskever, I. (2019). Language Models are Unsupervised Multitask Learners. OpenAI Technical Report.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Aliasnamen	BERT İnce Ayar (Fine-Tuning), BERT ince ayar, fine-tuning BERT, transfer learning with BERT	GPT İnce Ayar ve Talimat Uyarlaması, GPT fine-tuning, instruction tuning, LLM fine-tuning	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Verwandt	5	5	5
Zusammenfassung	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.	GPT fine-tuning adapts pretrained autoregressive language models such as GPT-2/3/4 or LLaMA — introduced in OpenAI's 2019 work by Radford and colleagues — to domain-specific data or to instruction following via reinforcement learning from human feedback (RLHF) or DPO. It is used for instruction following, domain adaptation, and generative tasks.	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).