Vision Transformers Quiz

Answers and explanations appear as you take the quiz.

1. 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
2. Which mechanism supports direct interactions between allowed patch tokens in the original dense ViT encoder?
   • Self-attention
   • Only a fixed local max-pooling operation
   • Only alphabetical ordering of patch labels
   • Only a random image crop
3. 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
4. What is the purpose of positional encodings in a Vision Transformer?
   • To compress the image file size
   • To randomly shuffle the patches for augmentation
   • To tell the model where each patch was located in the original image
   • To convert color images to grayscale
5. A practical drawback of self-attention over many image patches is that its cost grows:
   • Quadratically with the number of patches
   • Linearly with the number of patches
   • Not at all with image size
   • Only with the number of color channels
6. 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
7. 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
8. 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