Rain-Bus/Obsidian
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

vault backup: 2023-12-19 20:16:21

Browse Source
This commit is contained in:
Rain&Bus
2023-12-19 20:16:21 +08:00
parent 7d6c6e28da
commit f1bf108986
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Paper/Open-Vocabulary Semantic Segmentation.md
View File

@@ -10,6 +10,10 @@
1. Using ground-truth masks as region proposal. 1. Using ground-truth masks as region proposal.
2. Feed masked images to a pre-trained CLIP for classification. 2. Feed masked images to a pre-trained CLIP for classification.
3. Get mIoU of 20.1% on the ADE20K-150 dataset. 3. Get mIoU of 20.1% on the ADE20K-150 dataset.
4. Use MaskFormer(a mask proposal generator trained on COCO) as an region proposal generator.
5. Select the region proposals with highest overlap with ground-truth masks.
6. Assign the object label to this region.
7. This model reach mIoU of 66.5%(despite)
## Vocabularies ## Vocabularies