引導式測驗 · 中等 等級
基於區域的 CNN 測驗
測試區域建議、共享卷積特徵、RoI 操作、掩模以及兩級檢測器的精度與速度權衡。
問題 1 的 8
基於區域的 CNN 的核心思想是什麼?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 基於區域的 CNN 的核心思想是什麼?
- 提出候選區域,然後對每個區域中的物件進行分類和裝箱
- 為整個影像產生單一標籤
- 處理前壓縮影像
- 首先將影像轉換為灰階圖
- 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
- Faster R-CNN 引入了什麼來取代選擇性搜尋?
- 更大的 CNN 主幹網
- 灰階轉換步驟
- 區域提案網(RPN)
- 循環神經網絡
- RoI池化能實現什麼?
- 它刪除分數低的區域
- 它提高了圖像分辨率
- 它將所有區域合併為一個
- 它從每個區域的共享特徵圖中裁剪特徵並調整其大小
- Mask R-CNN 增加了哪些額外功能?
- 每個偵測到的物件的像素級分割遮罩
- 音訊轉錄
- 文字翻譯
- 單一像素的 3D 深度
- 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
- 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
- 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