Comparer des méthodes

	Segmentation d'instances	Détection d'objets
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2017	2014–2016
Auteur d'origine	He, K., Gkioxari, G., Dollar, P., Girshick, R.	Girshick, R. et al. (R-CNN); Redmon, J. et al. (YOLO)
Type	Pixel-level detection and mask prediction	Supervised deep learning (region proposal or single-shot)
Source fondatrice	He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2961–2969.	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.
Alias	instance-level segmentation, object instance segmentation, mask prediction, panoptic instance segmentation	visual object detection, image object localization, region-based object detection, bounding-box detection
Apparentées	4	3
Résumé	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.	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.