引导式测验 · 中等 等级

基于区域的 CNN 测验

测试区域提议、共享卷积特征、RoI 操作、掩模以及两级检测器的精度与速度权衡。

相关引导路径基于区域的CNN
问题 1 的 8

基于区域的 CNN 的核心思想是什么？

预览每个问题8 问题

当您参加测验时，就会出现答案和解释。

  1. 基于区域的 CNN 的核心思想是什么？
    • 提出候选区域，然后对每个区域中的对象进行分类和装箱
    • 为整个图像生成单个标签
    • 处理前压缩图像
    • 首先将图像转换为灰度图
  2. Why was the original R-CNN computationally expensive?
    • It trained without image pixels
    • It ran a CNN separately on each proposed region
    • It required one human label per test image
    • It computed only one shared feature map
  3. Faster R-CNN 引入了什么来取代选择性搜索？
    • 更大的 CNN 主干网
    • 灰度转换步骤
    • 区域提案网络（RPN）
    • 循环神经网络
  4. RoI池化能实现什么？
    • 它删除分数低的区域
    • 它提高了图像分辨率
    • 它将所有区域合并为一个
    • 它从每个区域的共享特征图中裁剪特征并调整其大小
  5. Mask R-CNN 添加了哪些额外功能？
    • 每个检测到的对象的像素级分割掩模
    • 音频转录
    • 文字翻译
    • 单个像素的 3D 深度
  6. What training objective does Mask R-CNN use for its classification, box, and mask branches?
    • Only a pixelwise mask loss with no classification
    • A multi-task loss that combines classification, bounding-box regression, and mask losses
    • A language-model next-token loss
    • A region-proposal loss with no object classification
  7. What alignment problem does RoIAlign address compared with RoI pooling?
    • It replaces the Region Proposal Network with Selective Search
    • It removes all need for a shared feature map
    • It avoids the coordinate quantization that can misalign extracted region features
    • It predicts a class label before processing the image
  8. How should two-stage and single-stage detector speed/accuracy be compared?
    • Two-stage models are always more accurate and faster
    • Single-stage models cannot detect multiple objects
    • The architectures have identical pipelines
    • Using a specified benchmark and implementation, because the tradeoff is not universal