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

Paper/Open-Vocabulary Semantic Segmentation.md

@@ -1,7 +1,19 @@
 ## Introduction
 - Two-stage approach
-	1. Generate class-agnostic mask proposal
+	- Method
-	2. 
+		1. Generate class-agnostic mask proposal.
+		2. Leverage pre-trained CLIP to perform open-vocabulary classification.
+	- Assumption
+		1. The model can generate classagnostic mask proposals.
+		2. Pre-trained CLIP can transfer its classification performance to masked image proposals.
+	- Examination
+		1. Using ground-truth masks as region proposal.
+		2. Feed masked images to a pre-trained CLIP for classification.
+		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