Порівняння методів
Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.
| Масковані автокодувальники× | Модель сегментації всього (Segment Anything Model)× | |
|---|---|---|
| Галузь | Глибоке навчання | Глибоке навчання |
| Родина | Machine learning | Machine learning |
| Рік появи≠ | 2021 | 2023 |
| Автор методу≠ | Kaiming He | Alexander Kirillov |
| Тип | Neural network architecture | Neural network architecture |
| Основоположне джерело≠ | He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000-16009). DOI ↗ | 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 ↗ |
| Інші назви | MAE, Vision MAE | SAM, Segment Anything |
| Пов'язані | 4 | 4 |
| Підсумок≠ | Masked Autoencoders (MAE) is a self-supervised learning approach introduced by He et al. in 2021 that masks random patches of an image and trains a model to reconstruct the missing content. Adapting the masked language modeling paradigm from NLP to vision, MAE learns rich visual representations by solving a challenging reconstruction task without requiring labels. | 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. |
| ScholarGateНабір даних ↗ |
|
|