search

thunlp / PEVL

Source code for EMNLP 2022 paper “PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models”
MIT License
47 stars 5 forks source link

Query regarding downstream task #2

Closed sauradip closed 2 years ago

sauradip commented 2 years ago

Hi AUthors,

Thanks for making code available for this awesome work. My question is like Pix2seq did for object detection , can this work can be applied to dense prediction task like : Semantic Segmentation etc ?

qyc-98 commented 2 years ago

Hi, intuitively, it is possible to apply PEVL to semantic segmentation. You can refer to this paper, basically, you just need to replace 'tree', 'sidewalk', 'person' with your query text label.