← 返回卡片

原书出处

Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)

核验版本的摘录快照 · 导入于 2026-11-14T15:40:56.557Z

A result of this analysis is we may explicit decompose contrastive learning into one loss for alignment and another for uniformity, with the following forms: (30.13) (30.14) (30.15) where ppos is the distribution of positive pairs and α, t, and λ are hyperparameters of the losses. 30.10.2 Experiment: Designing Embeddings with Contrastive Learning Using the alignment and uniformity objective defined previously, we will now illustrate

此预览只包含定位所需的摘录和上下文。

原书定位详情

来源:a19c7933-4eda-4176-aebd-30fe7e1ad292

正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c030b.xhtml

EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8