Input to text-encoder - Githubissues

KU-CVLAB / CAT-Seg

Official Implementation of "CAT-Seg🐱: Cost Aggregation for Open-Vocabulary Semantic Segmentation"

https://ku-cvlab.github.io/CAT-Seg/

MIT License

247 stars 25 forks source link

Input to text-encoder #27

Closed Zhirui86 closed 3 months ago

Zhirui86 commented 3 months ago

Hi! @Seokju-Cho Thanks for your inspiring work! You mentioned in your paper that the text-encoder accepts input like "A photo of a {class}", I'm wondering if I want to train your model on my own dataset which only offers fully-supervised label(pixel-wise label),how can I make it? Thanks in advance. Best, Zhirui