Methoden vergleichen
Prüfen Sie die ausgewählten Methoden nebeneinander; abweichende Zeilen sind hervorgehoben.
| Instanzsegmentierung× | Bildklassifizierung× | |
|---|---|---|
| Fachgebiet | Deep Learning | Deep Learning |
| Familie | Machine learning | Machine learning |
| Entstehungsjahr≠ | 2017 | 2012 (deep CNN era); conceptual roots 1989 (LeCun) |
| Urheber≠ | He, K., Gkioxari, G., Dollar, P., Girshick, R. | Krizhevsky, A.; Sutskever, I.; Hinton, G. E. |
| Typ≠ | Pixel-level detection and mask prediction | Supervised classification task |
| Wegweisende Quelle≠ | He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2961–2969. DOI ↗ | 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. link ↗ |
| Aliasnamen | instance-level segmentation, object instance segmentation, mask prediction, panoptic instance segmentation | visual classification, image recognition, CNN-based classification, visual categorization |
| Verwandt≠ | 4 | 5 |
| Zusammenfassung≠ | 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. | 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. |
| ScholarGateDatensatz ↗ |
|
|