CLIP, OpenCLIP, and SigLIP: Contrastive Language-Image Pretraining

4 selectedDifficulty 5-64 unseenView topic

IntermediateNew

0 answered

4 intermediateAdapts to your performance

Question 1 of 4

120sintermediate (5/10)state theorem

Which expression correctly captures the symmetric CLIP contrastive objective for a batch of N image-text pairs with normalized embeddings v_{i}, u_{i} and learned temperature τ ?