Porovnať metódy

	Detekcia objektov	Klasifikácia obrazu	Inštancová segmentácia
Odbor	Hlboké učenie	Hlboké učenie	Hlboké učenie
Rodina	Machine learning	Machine learning	Machine learning
Rok vzniku	2014–2016	2012 (deep CNN era); conceptual roots 1989 (LeCun)	2017
Tvorca	Girshick, R. et al. (R-CNN); Redmon, J. et al. (YOLO)	Krizhevsky, A.; Sutskever, I.; Hinton, G. E.	He, K., Gkioxari, G., Dollar, P., Girshick, R.
Typ	Supervised deep learning (region proposal or single-shot)	Supervised classification task	Pixel-level detection and mask prediction
Pôvodný zdroj	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.	Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems (NeurIPS), 25, 1097–1105.	He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2961–2969.
Ďalšie názvy	visual object detection, image object localization, region-based object detection, bounding-box detection	visual classification, image recognition, CNN-based classification, visual categorization	instance-level segmentation, object instance segmentation, mask prediction, panoptic instance segmentation
Príbuzné	3	5	4
Zhrnutie	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.	Image classification is the task of assigning a single semantic label to an entire image from a fixed set of categories. Modern approaches rely on deep convolutional neural networks (CNNs) or Vision Transformers (ViTs) trained end-to-end on large labeled datasets such as ImageNet, achieving superhuman accuracy on many benchmarks and underpinning applications from medical imaging to autonomous vehicles.	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.