← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8978 · 生成模型:GPT-6

共现线索不等于对象同一

理解等级:中级

同图不同视图通常共享场景信息,可作为自监督表示的训练线索。但同一图中也包含多个物体,不同图也可能出现同一类物体。将图像级视图关系用于密集区域分组是一种归纳假设,不能把“同图”直接当作精确像素同实例标签。

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

      Because human supervision is expensive and limiting, a popular alternative is to use self-supervised affinity measures, just like we saw in self-supervised contrastive learning. Popular contrastive learning methods like SimCLR [79], MoCo [193], and DINO [70], train a mapping from image patches to embedding vectors such that two patches that come from the same image embed near each other and patches from different images embed

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第31章《知觉分组》(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/c031.xhtml) - 结论依据:摘录中关于共现线索不等于对象同一的定义、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:Because human supervision is expensive and limiting, a popular alternative is to use self-supervised affinity measures, just like we saw in self-supervised contrastive learning. Popular contrastive learning methods like SimCLR [79], MoCo [193], and DINO [70], train a mapping from image patches to embedding vectors such that two patches that come from the same image embed near each other and patches from different images embed