search

MendelXu / SAN

Open-vocabulary Semantic Segmentation
https://mendelxu.github.io/SAN/
MIT License
295 stars 27 forks source link

pointsample #24

Closed sunwhw closed 9 months ago

sunwhw commented 12 months ago

When compare the predition_mask with gt_mask, i find you used the pointsample() to align their size, do you think it harms the learning performance? Have you ever tried other methods or the pointsample() is always used for detr's-like model?

MendelXu commented 12 months ago

Sorry, we didn't ablate its neceesarity. However, you can refer to the original mask2former paper, it seems the pointsample would not downgrade the performance.

sunwhw commented 11 months ago

oh! Well! Thanks!