方法对比

	语义分割	微调语义分割
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2015	2015–2018
提出者	Long, J., Shelhamer, E., & Darrell, T.	Long, Shelhamer & Darrell (FCN); Chen et al. (DeepLab)
类型	Dense prediction / pixel-wise classification	Transfer learning / dense prediction
开创性文献	Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440.	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.
别名	pixel-wise classification, scene parsing, dense labeling, semantic scene segmentation	fine-tuned semseg, domain-adapted semantic segmentation, transfer learning semantic segmentation, pretrained dense prediction fine-tuning
相关	5	4
摘要	Semantic segmentation assigns a class label to every pixel in an image, producing a dense, category-annotated map of the scene. Unlike object detection, which draws bounding boxes, it delineates the exact spatial extent of each class, making it indispensable in medical imaging, autonomous driving, satellite analysis, and any task where precise region boundaries matter.	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.