方法对比

	弱监督视觉变换器	自监督学习
领域	深度学习	机器学习
方法族	Machine learning	Machine learning
起源年份	2021–2022	2018–2020
提出者	Dosovitskiy et al. (ViT); weak supervision paradigm from Zhou and others	LeCun, Y. and community (formalized ~2018–2020)
类型	Self-attention image model with weakly supervised training	Representation learning paradigm
开创性文献	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).	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/
别名	WS-ViT, weakly supervised ViT, weak supervision with vision transformer, ViT with weak labels	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
相关	4	3
摘要	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.	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.