Сравнение методов

	Трансформер зрения со слабой разметкой (WS-ViT)	Vision Transformer
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2021–2022	2021
Автор метода	Dosovitskiy et al. (ViT); weak supervision paradigm from Zhou and others	Dosovitskiy, A. et al.
Тип	Self-attention image model with weakly supervised training	Transformer architecture for images (self-attention over patches)
Основополагающий источник	Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (ICLR).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Другие названия	WS-ViT, weakly supervised ViT, weak supervision with vision transformer, ViT with weak labels	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Связанные	4	5
Сводка	Weakly Supervised Vision Transformer (WS-ViT) trains a Vision Transformer on image data that lacks precise pixel-level annotations, instead using cheaper, noisier supervision such as image-level class tags, bounding boxes, or web-scraped text. The global self-attention mechanism of the transformer makes it especially capable of localising objects and learning discriminative features from these incomplete 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).