← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9113 · 生成模型:GPT-6

模型比较需同时检查域内域外

理解等级:中级

手工简单世界系统在其几何与外观假设成立时可有清晰重建,变化光照或背景后可能连锁失败。预训练模型在展示中适用更多外观,却仍有形变;这些定性例展示权衡,不足以给出所有场景下可靠性的统计排名。

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

      Figure 55.5: Out of domain generalization. For the pretrained model, these images might still be within the domain of the training, as it contained a very diverse set of natural images. The simple system model only works for the first example and breaks down for the rest, producing completely wrong reconstructions.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第55章《重访简单视觉系统》(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/c055b.xhtml) - 结论依据:摘录中关于模型比较需同时检查域内域外的定义、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:Figure 55.5: Out of domain generalization. For the pretrained model, these images might still be within the domain of the training, as it contained a very diverse set of natural images. The simple system model only works for the first example and breaks down for the rest, producing completely wrong reconstructions.