Easy
DeepLearn
Categories
Resources
Progress
← Back to flashcards
1 / 214 · Score 0
Quiz —
Unsupervised Learning
Question 1
Zero-shot image classification via CLIP — mechanism.
A.
Same as fine-tune
B.
Encode class names as 'a photo of {class}' text + image; cosine max = prediction; no label training; prompt-sensitive; foundation of open-vocab detection (OWL-ViT, GLIP)
C.
Random
D.
Not real
Next question →