search

Markin-Wang / XProNet

[ECCV2022] The official implementation of Cross-modal Prototype Driven Network for Radiology Report Generation
Apache License 2.0
65 stars 9 forks source link

How to get the init_prototypes.pt ？ #5

Closed zycleo closed 2 years ago

zycleo commented 2 years ago

Dear author, I wonder if you got the prototype, did you first use a pretrained model to extract visual and textual features, then concatenate the visual and textual features, cluster 20 clusters with k-means? Normalize before clustering? Use each cluster center as a prototype? Could you please explain it in detail?Thank you very much.

Markin-Wang commented 2 years ago

Dear author, I wonder if you got the prototype, did you first use a pretrained model to extract visual and textual features, then concatenate the visual and textual features, cluster 20 clusters with k-means? Normalize before clustering? Use each cluster center as a prototype? Could you please explain it in detail?Thank you very much.

Hi, thanks for your interest. Yes, the details are mentioned in our paper which are the same as you said.