search

CVMI-Lab / PLA

(CVPR 2023) PLA: Language-Driven Open-Vocabulary 3D Scene Understanding & (CVPR2024) RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding
Apache License 2.0
256 stars 11 forks source link

caption_idx #14

Closed gbliao closed 5 months ago

gbliao commented 1 year ago

Hi, thanks for your great work! I understand the meaning of equation (18). But I found in the code that the target of the loss function is caption_idx, is it convenient for you to explain the exact meaning of caption_idx?

Dingry commented 1 year ago

Hi, caption_idx means the label index for each pooled 3D feature. Since we remove duplicate captions in a batch, we need to record the label index to make sure the correspondence between the 3D feature and the language feature.

gbliao commented 1 year ago

Thank you for your response. Can I understand that the label is the language feature?