Uporedite metode
Pregledajte izabrane metode jednu pored druge; redovi koji se razlikuju su istaknuti.
| Detekcija objekata sa malo primera (FSOD)× | Masked Autoencoders× | Vision Transformer× | |
|---|---|---|---|
| Oblast | Duboko učenje | Duboko učenje | Duboko učenje |
| Porodica | Machine learning | Machine learning | Machine learning |
| Godina nastanka≠ | 2020 | 2021 | 2021 |
| Tvorac≠ | Xin Wang | Kaiming He | Dosovitskiy, A. et al. |
| Tip≠ | Neural network architecture | Neural network architecture | Transformer architecture for images (self-attention over patches) |
| Temeljni izvor≠ | 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 ↗ | 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 ↗ | Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗ |
| Drugi nazivi≠ | FSOD, Few-shot detection | MAE, Vision MAE | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images |
| Srodne≠ | 3 | 4 | 5 |
| Sažetak≠ | 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. | 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. | 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). |
| ScholarGateSkup podataka ↗ |
|
|
|