High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zeng, Quan-Sheng, Li, Yunheng, Zhou, Daquan, Li, Guanbin, Hou, Qibin, Cheng, Ming-Ming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929754965278720
author Zeng, Quan-Sheng
Li, Yunheng
Zhou, Daquan
Li, Guanbin
Hou, Qibin
Cheng, Ming-Ming
author_facet Zeng, Quan-Sheng
Li, Yunheng
Zhou, Daquan
Li, Guanbin
Hou, Qibin
Cheng, Ming-Ming
contents Open-vocabulary image segmentation has been advanced through the synergy between mask generators and vision-language models like Contrastive Language-Image Pre-training (CLIP). Previous approaches focus on generating masks while aligning mask features with text embeddings during training. In this paper, we observe that relying on generated low-quality masks can weaken the alignment of vision and language in regional representations. This motivates us to present a new fine-tuning framework, named MaskCLIP++, which uses ground-truth masks instead of generated masks to enhance the mask classification capability of CLIP. Due to the limited diversity of image segmentation datasets with mask annotations, we propose incorporating a consistency alignment principle during fine-tuning, which alleviates categorical bias toward the fine-tuning dataset. After low-cost fine-tuning, MaskCLIP++ significantly improves the mask classification performance on multi-domain datasets. Combining with the mask generator in previous state-of-the-art mask-based open vocabulary segmentation methods, we achieve performance improvements of +1.7, +2.3, +2.1, +3.1, and +0.3 mIoU on the A-847, PC-459, A-150, PC-59, and PAS-20 datasets, respectively. Code is avaliable at https://github.com/HVision-NKU/MaskCLIPpp .
format Preprint
id arxiv_https___arxiv_org_abs_2412_11464
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation
Zeng, Quan-Sheng
Li, Yunheng
Zhou, Daquan
Li, Guanbin
Hou, Qibin
Cheng, Ming-Ming
Computer Vision and Pattern Recognition
Open-vocabulary image segmentation has been advanced through the synergy between mask generators and vision-language models like Contrastive Language-Image Pre-training (CLIP). Previous approaches focus on generating masks while aligning mask features with text embeddings during training. In this paper, we observe that relying on generated low-quality masks can weaken the alignment of vision and language in regional representations. This motivates us to present a new fine-tuning framework, named MaskCLIP++, which uses ground-truth masks instead of generated masks to enhance the mask classification capability of CLIP. Due to the limited diversity of image segmentation datasets with mask annotations, we propose incorporating a consistency alignment principle during fine-tuning, which alleviates categorical bias toward the fine-tuning dataset. After low-cost fine-tuning, MaskCLIP++ significantly improves the mask classification performance on multi-domain datasets. Combining with the mask generator in previous state-of-the-art mask-based open vocabulary segmentation methods, we achieve performance improvements of +1.7, +2.3, +2.1, +3.1, and +0.3 mIoU on the A-847, PC-459, A-150, PC-59, and PAS-20 datasets, respectively. Code is avaliable at https://github.com/HVision-NKU/MaskCLIPpp .
title High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.11464