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

vault backup: 2023-12-19 20:31:21

Browse Source
This commit is contained in:
Rain&Bus
2023-12-19 20:31:21 +08:00
parent f1bf108986
commit 36034a9d51
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
Paper/Open-Vocabulary Semantic Segmentation.md
View File

@@ -13,8 +13,9 @@
4. Use MaskFormer(a mask proposal generator trained on COCO) as an region proposal generator. 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. 5. Select the region proposals with highest overlap with ground-truth masks.
6. Assign the object label to this region. 6. Assign the object label to this region.
7. This model reach mIoU of 66.5%(despite) 7. This model reach mIoU of 66.5%. (despite imperfect region proposal)
- Conclusion
Pre-trained CLIP not performed well over masked images, we hypothesize that CLIP trained on natural image which are not cropped or noised by segmentation masks.
## Vocabularies ## Vocabularies
1. ground-truth masks: refer to the manually annotated masks or pixel-level labels that are used to define the correct segmentation of objects in an image. Each pixel in the ground-truth mask is assigned a specific class label corresponding to the object or region it belongs to. 1. ground-truth masks: refer to the manually annotated masks or pixel-level labels that are used to define the correct segmentation of objects in an image. Each pixel in the ground-truth mask is assigned a specific class label corresponding to the object or region it belongs to.