方法对比

	视觉对比学习	长格式Transformer / BigBird
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2020	2020
提出者	Chen, T. et al. (SimCLR); He, K. et al. (MoCo)	Beltagy, Peters & Cohan (Longformer); Zaheer et al. (BigBird)
类型	Self-supervised deep representation learning	Sparse-attention Transformer for long sequences
开创性文献	Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. ICML.	Beltagy, I., Peters, M. E. & Cohan, A. (2020). Longformer: The Long-Document Transformer. arXiv.
别名	Karşıtlık Öğrenmesi — Görsel (SimCLR / MoCo / BYOL), contrastive learning, self-supervised visual representation learning, SimCLR	Uzun Dizi Transformer (Longformer / BigBird), uzun dizi transformer, long-document transformer, sparse-attention transformer
相关	5	4
摘要	Visual contrastive learning is a self-supervised deep-learning approach — popularised by frameworks such as SimCLR (Chen et al., 2020) and MoCo (He et al., 2020) — that learns rich image representations without labels by pulling different augmentations of the same image together and pushing different images apart. It turns a large pool of unlabelled images into a useful feature extractor.	Long-sequence Transformers such as Longformer (Beltagy, Peters & Cohan, 2020) and BigBird (Zaheer et al., 2020) replace the standard Transformer's O(n²) attention with sparse attention patterns that scale linearly, O(n), with sequence length. This lets a single model attend over thousands of tokens — full documents, legal texts, or genomic sequences — that would not fit a conventional Transformer.