Сравнение на методи
Прегледайте избраните методи един до друг; редовете с разлики са откроени.
| SimCLR× | Детекция на обекти с малко примери (Few-Shot Object Detection)× | Vision Transformer× | |
|---|---|---|---|
| Област | Дълбоко обучение | Дълбоко обучение | Дълбоко обучение |
| Семейство | Machine learning | Machine learning | Machine learning |
| Година на възникване≠ | 2020 | 2020 | 2021 |
| Създател≠ | Ting Chen | Xin Wang | Dosovitskiy, A. et al. |
| Тип≠ | Neural network architecture | Neural network architecture | Transformer architecture for images (self-attention over patches) |
| Основополагащ източник≠ | Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In International conference on machine learning (pp. 1597-1607). PMLR. link ↗ | Wang, X., Huang, T. E., Darrell, T., Gonzalez, J. E., & Yu, F. (2020). Few-shot object detection with attention-RPN and multi-relation detector. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9050-9059). link ↗ | Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗ |
| Други названия≠ | Simple contrastive learning, SimCLR framework | FSOD, Few-shot detection | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images |
| Свързани≠ | 4 | 3 | 5 |
| Резюме≠ | SimCLR is a self-supervised learning framework introduced by Chen et al. in 2020 that learns visual representations by contrasting similar and dissimilar views of images. The method applies strong data augmentations to create different views of the same image, then trains an encoder to bring similar views close in representation space while pushing dissimilar views apart. | Few-Shot Object Detection (FSOD) is a meta-learning approach that enables detecting novel object classes from only a few annotated examples. Unlike standard object detection requiring hundreds of labeled instances per class, FSOD learns to quickly adapt detection models to new object categories by leveraging knowledge from base categories. | The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs). |
| ScholarGateНабор от данни ↗ |
|
|
|