방법 비교

	인스턴스 분할	Semantic segmentation	Vision Transformer
분야	딥러닝	딥러닝	딥러닝
계열	Machine learning	Machine learning	Machine learning
기원 연도	2017	2015	2021
창시자	He, K., Gkioxari, G., Dollar, P., Girshick, R.	Long, J., Shelhamer, E., & Darrell, T.	Dosovitskiy, A. et al.
유형	Pixel-level detection and mask prediction	Dense prediction / pixel-wise classification	Transformer architecture for images (self-attention over patches)
원전	He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2961–2969.	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.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
별칭	instance-level segmentation, object instance segmentation, mask prediction, panoptic instance segmentation	pixel-wise classification, scene parsing, dense labeling, semantic scene segmentation	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
관련	4	5	5
요약	Instance segmentation is a computer vision task that simultaneously detects every distinct object in an image and produces a precise pixel-level mask for each individual object instance. Unlike semantic segmentation, which labels every pixel with a class, instance segmentation distinguishes between separate objects of the same class, enabling fine-grained spatial understanding.	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.	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).