Порівняння методів
Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.
| Модель сегментації всього (Segment Anything Model)× | DETR (Detection Transformer)× | |
|---|---|---|
| Галузь | Глибоке навчання | Глибоке навчання |
| Родина | Machine learning | Machine learning |
| Рік появи≠ | 2023 | 2020 |
| Автор методу≠ | Alexander Kirillov | Nicolas Carion |
| Тип | Neural network architecture | Neural network architecture |
| Основоположне джерело≠ | Kirillov, A., Mintun, E., Darrell, T., & Girshick, R. (2023). Segment Anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 4015-4026). DOI ↗ | Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European Conference on Computer Vision (pp. 213-229). Springer, Cham. DOI ↗ |
| Інші назви | SAM, Segment Anything | Detection Transformer, DETR |
| Пов'язані | 4 | 4 |
| Підсумок≠ | Segment Anything Model (SAM) is a foundation model introduced by Kirillov et al. in 2023 that can segment any object in an image given various forms of prompts. SAM is trained on a massive dataset of diverse images and learns to segment objects based on minimal user input such as points, boxes, or text descriptions. | DETR (Detection Transformer) is an end-to-end framework for object detection introduced by Carion et al. in 2020 that reformulates detection as a direct set prediction problem using transformers. Unlike traditional approaches that use hand-crafted post-processing like non-maximum suppression, DETR treats object detection as a sequence-to-sequence problem where the transformer predicts all objects at once. |
| ScholarGateНабір даних ↗ |
|
|