방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| Semantic segmentation× | 인스턴스 분할× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2015 | 2017 |
| 창시자≠ | Long, J., Shelhamer, E., & Darrell, T. | He, K., Gkioxari, G., Dollar, P., Girshick, R. |
| 유형≠ | Dense prediction / pixel-wise classification | Pixel-level detection and mask prediction |
| 원전≠ | 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. DOI ↗ | 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 ↗ |
| 별칭 | pixel-wise classification, scene parsing, dense labeling, semantic scene segmentation | instance-level segmentation, object instance segmentation, mask prediction, panoptic instance segmentation |
| 관련≠ | 5 | 4 |
| 요약≠ | 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. | 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. |
| ScholarGate데이터셋 ↗ |
|
|