引導式測驗 · 中等 等級
視覺變形金剛測驗
透過原始研究結果、位置資訊、補丁計數和分類狀態選擇,探索 ViT 的補丁標記和注意力。
問題 1 的 8
How does the original plain ViT convert an image into input tokens for its encoder?
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。
- How does the original plain ViT convert an image into input tokens for its encoder?
- It must read one raw pixel per recurrent step
- It linearly embeds flattened non-overlapping patches
- It converts the whole image into a mandatory single scalar
- It removes all learned input projections
- Which mechanism supports direct interactions between allowed patch tokens in the original dense ViT encoder?
- 自我關注
- Only a fixed local max-pooling operation
- Only alphabetical ordering of patch labels
- Only a random image crop
- Which architectural difference did the original ViT study discuss relative to convolutional networks?
- A guarantee that it contains fewer parameters than every CNN
- An inability to process color images
- A guarantee that every vision task needs the same huge dataset
- Fewer convolution-style locality and translation-equivariance biases
- Vision Transformer 中位置編碼的目的是什麼?
- 壓縮圖像檔案大小
- 隨機打亂補丁以進行增強
- 告訴模型每個補丁在原始影像中的位置
- 將彩色影像轉換為灰階影像
- 對許多影像區塊進行自註意力的實際缺點是其成本會增加:
- 與補丁數量成二次方
- 與補丁數量成線性關係
- 與影像大小完全無關
- 僅與顏色通道數有關
- What conclusion is supported by the original ViT classification experiments under their stated pretraining and transfer conditions?
- Every transformer must outperform every CNN on every dataset
- A pure patch transformer could perform competitively with compared CNNs
- All convolutional operations are invalid for image recognition
- No training data is needed for image classification
- For a 224-by-224 image divided into non-overlapping 16-by-16 patches, how many patch tokens are there before adding a class token?
- 197
- 224
- 196
- 256
- In the original ViT classification design, which encoder state supplies the classification head?
- Only an unembedded raw input pixel
- A required random token not processed by the encoder
- Only the first patch’s original filename
- The final state of the learned class token