← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 9002.e · 生成模型:GPT-6

跨数据样本价值不对称

理解等级:中级

将某来源样本折算成目标测试域的等效样本数,是任务和评估条件下的经验比较。书中 2011 年汽车分类表按目标市场列出不对称比例;零值不意味着该来源对所有任务没有信息。使用这类表必须带上年代、类别、模型和目标测试分布。

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

      In table 35.2, each number represents the value of one training example from one dataset when used to test on another. A value of 0.25 means that you need 4 times more training examples than when using a sample derived from the same testing distribution. These results are from 2011 [471] and computer vision datasets have evolved since then.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第35章《数据偏差与分布漂移》(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/c035b.xhtml) - 结论依据:摘录中关于跨数据样本价值不对称的定义、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:In table 35.2, each number represents the value of one training example from one dataset when used to test on another. A value of 0.25 means that you need 4 times more training examples than when using a sample derived from the same testing distribution. These results are from 2011 [471] and computer vision datasets have evolved since then.