Сравнение на методи

	Фино настроена семантична сегментация	Фина настройка на конволюционна невронна мрежа
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2015–2018	2012–2014
Създател	Long, Shelhamer & Darrell (FCN); Chen et al. (DeepLab)	Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward
Тип	Transfer learning / dense prediction	Transfer learning technique (supervised fine-tuning)
Основополагащ източник	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.	Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27.
Други названия	fine-tuned semseg, domain-adapted semantic segmentation, transfer learning semantic segmentation, pretrained dense prediction fine-tuning	Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network
Свързани	4	5
Резюме	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-tuning a CNN means starting from a network already trained on a large dataset — typically ImageNet — and continuing training on a smaller target dataset so the model adapts its learned visual features to a new task. This approach dramatically reduces the data and compute required to reach strong performance compared with training from scratch.