方法对比

	微调语义分割	微调视觉Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2015–2018	2020-2021
提出者	Long, Shelhamer & Darrell (FCN); Chen et al. (DeepLab)	Dosovitskiy, A. et al. (Google Brain)
类型	Transfer learning / dense prediction	Transfer learning / fine-tuning of attention-based image model
开创性文献	Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3431–3440.	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).
别名	fine-tuned semseg, domain-adapted semantic segmentation, transfer learning semantic segmentation, pretrained dense prediction fine-tuning	Fine-Tuned ViT, ViT fine-tuning, Vision Transformer transfer learning, ViT downstream adaptation
相关	4	5
摘要	Fine-tuned semantic segmentation adapts a deep neural network pre-trained on a large pixel-labelled dataset (e.g., ImageNet-pretrained backbone with an encoder-decoder head trained on COCO or Cityscapes) to a new target domain by continuing training on domain-specific annotated images. The result is a model that assigns a class label to every pixel in an image while leveraging rich visual representations learned from vastly more data than the target domain alone could provide.	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.