手法を比較

	セマンティックセグメンテーション	物体検出
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2015	2014–2016
提唱者	Long, J., Shelhamer, E., & Darrell, T.	Girshick, R. et al. (R-CNN); Redmon, J. et al. (YOLO)
種類	Dense prediction / pixel-wise classification	Supervised deep learning (region proposal or single-shot)
原典	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.	Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 580–587.
別名	pixel-wise classification, scene parsing, dense labeling, semantic scene segmentation	visual object detection, image object localization, region-based object detection, bounding-box detection
関連	5	3
概要	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.	Object detection is a computer vision task in which a deep neural network simultaneously locates and classifies every instance of one or more object categories within an image, producing a bounding box and a class label for each detected object. Modern detectors — from the R-CNN family to YOLO and DETR — achieve near-human accuracy at real-time speeds on standard benchmarks.