From 7d6c6e28da6a1fe4a78014e4ff2090fd2bd6a8a3 Mon Sep 17 00:00:00 2001 From: RainBus Date: Tue, 19 Dec 2023 20:01:21 +0800 Subject: [PATCH] vault backup: 2023-12-19 20:01:21 --- Paper/Open-Vocabulary Semantic Segmentation.md | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/Paper/Open-Vocabulary Semantic Segmentation.md b/Paper/Open-Vocabulary Semantic Segmentation.md index 0d9443d..4bd3882 100644 --- a/Paper/Open-Vocabulary Semantic Segmentation.md +++ b/Paper/Open-Vocabulary Semantic Segmentation.md @@ -1,7 +1,15 @@ ## Introduction - Two-stage approach - 1. Generate class-agnostic mask proposal - 2. + - Method + 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. ## Vocabularies