← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8974.c · 生成模型:GPT-6

信息对比视为候选分类

理解等级:中级

InfoNCE将锚点与正候选、多个负候选的相似度除以正温度τ,经Softmax得到候选分布,再最小化正候选的负对数概率。分母包含正候选本身;用点积作为相似度时数值越大越接近,不能与距离越大越不相似的符号混用。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      Notice that the InfoNCE loss is a log softmax over a vector of scores f1(x)Tf2(c)/τ with ; you can therefore think of this loss as corresponding to a classification problem where the ground truth class is x+ and the other possible classes are (refer to chapter 9 to revisit softmax classification).

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第30章《表示学习》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c030b.xhtml) - 结论依据:摘录中关于信息对比视为候选分类的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:Notice that the InfoNCE loss is a log softmax over a vector of scores f1(x)Tf2(c)/τ with ; you can therefore think of this loss as corresponding to a classification problem where the ground truth class is x+ and the other possible classes are (refer to chapter 9 to revisit softmax classification).