引導式測驗 · 硬 等級
Swin 變壓器測驗
檢查 Swin 中的移動視窗注意力、跨視窗通訊、分層特徵、補丁合併和視覺任務應用。
問題 1 的 8
Swin Transformer 中的「Swin」代表什麼?
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。
- Swin Transformer 中的「Swin」代表什麼?
- 移動視窗
- 光滑的窗戶
- 空間纏繞
- 單一窗口
- Swin 在每個本地關注視窗中添加哪些位置資訊?
- Absolute word embeddings from a text tokenizer
- A learnable relative-position bias
- A global convolution kernel shared across all windows
- A class-specific bounding-box regression target
- Swin 如何讓資訊在不同的視窗之間移動?
- 它使用循環連接
- 它完全刪除視窗邊界
- 它以交替的層數移動視窗分區
- 它只使用一個全域視窗
- Swin 階段之間的補丁合併圖層有何作用?
- 提高解析度並刪除通道
- 隨機掉落補丁
- 將補丁翻譯成文字
- 合併相鄰的補丁,降低解析度並增加通道
- 為什麼 Swin 的分層、多尺度輸出特別有用?
- 它巧妙地插入需要特徵金字塔的檢測和分割框架中
- 它僅有助於單一標籤分類
- 它消除了對標記資料的需要
- 它使模型比任何 CNN 都小
- How does Swin’s attention pattern differ from standard ViT attention?
- Swin has no attention mechanism
- Swin computes attention in local windows and shifts partitions between blocks; standard ViT uses global patch attention
- ViT uses only local convolutions
- Both always use identical global attention
- What scaling property does fixed-size window attention provide in Swin?
- It is independent of image resolution
- It becomes quadratic in channel count only
- Attention computation grows linearly with image size for fixed window size
- It removes all attention computation
- Why does shifted-window attention use a mask after the cyclic shift?
- To force every patch to attend to every image patch
- To remove all positional information
- To convert window attention into a convolution
- To prevent tokens from attending across boundaries that should remain separate windows