知识卡片
表示用途决定保留哪一端
若关注随机生成,可主要使用VAE的先验与解码器;若关注数据表示,可保留编码器的均值或分布参数用于下游。两种用途共享训练框架,但压缩质量、采样质量、后验准确性与任务表现仍需分别评估。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
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
One perspective on VAEs is that they are a way to train a generative model pθ. From this perspective, the encoder is just scaffolding for learning a decoder. However, the encoder can also be useful as an end in itself, and we might instead think of the decoder as scaffolding for training an encoder. This was the perspective presented by autoencoders, after all, and the
参考来源
- 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第33章《生成建模与表示学习》(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/c033.xhtml)
- 结论依据:摘录中关于表示用途决定保留哪一端的定义、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:One perspective on VAEs is that they are a way to train a generative model pθ. From this perspective, the encoder is just scaffolding for learning a decoder. However, the encoder can also be useful as an end in itself, and we might instead think of the decoder as scaffolding for training an encoder. This was the perspective presented by autoencoders, after all, and the