Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Ji-Jia, Chang, Andy Chia-Hao, Chuang, Chieh-Yu, Chen, Chun-Pei, Liu, Yu-Lun, Chen, Min-Hung, Hu, Hou-Ning, Chuang, Yung-Yu, Lin, Yen-Yu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2404.04231
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910399869222912
author Wu, Ji-Jia
Chang, Andy Chia-Hao
Chuang, Chieh-Yu
Chen, Chun-Pei
Liu, Yu-Lun
Chen, Min-Hung
Hu, Hou-Ning
Chuang, Yung-Yu
Lin, Yen-Yu
author_facet Wu, Ji-Jia
Chang, Andy Chia-Hao
Chuang, Chieh-Yu
Chen, Chun-Pei
Liu, Yu-Lun
Chen, Min-Hung
Hu, Hou-Ning
Chuang, Yung-Yu
Lin, Yen-Yu
contents This paper addresses text-supervised semantic segmentation, aiming to learn a model capable of segmenting arbitrary visual concepts within images by using only image-text pairs without dense annotations. Existing methods have demonstrated that contrastive learning on image-text pairs effectively aligns visual segments with the meanings of texts. We notice that there is a discrepancy between text alignment and semantic segmentation: A text often consists of multiple semantic concepts, whereas semantic segmentation strives to create semantically homogeneous segments. To address this issue, we propose a novel framework, Image-Text Co-Decomposition (CoDe), where the paired image and text are jointly decomposed into a set of image regions and a set of word segments, respectively, and contrastive learning is developed to enforce region-word alignment. To work with a vision-language model, we present a prompt learning mechanism that derives an extra representation to highlight an image segment or a word segment of interest, with which more effective features can be extracted from that segment. Comprehensive experimental results demonstrate that our method performs favorably against existing text-supervised semantic segmentation methods on six benchmark datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2404_04231
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation
Wu, Ji-Jia
Chang, Andy Chia-Hao
Chuang, Chieh-Yu
Chen, Chun-Pei
Liu, Yu-Lun
Chen, Min-Hung
Hu, Hou-Ning
Chuang, Yung-Yu
Lin, Yen-Yu
Computer Vision and Pattern Recognition
This paper addresses text-supervised semantic segmentation, aiming to learn a model capable of segmenting arbitrary visual concepts within images by using only image-text pairs without dense annotations. Existing methods have demonstrated that contrastive learning on image-text pairs effectively aligns visual segments with the meanings of texts. We notice that there is a discrepancy between text alignment and semantic segmentation: A text often consists of multiple semantic concepts, whereas semantic segmentation strives to create semantically homogeneous segments. To address this issue, we propose a novel framework, Image-Text Co-Decomposition (CoDe), where the paired image and text are jointly decomposed into a set of image regions and a set of word segments, respectively, and contrastive learning is developed to enforce region-word alignment. To work with a vision-language model, we present a prompt learning mechanism that derives an extra representation to highlight an image segment or a word segment of interest, with which more effective features can be extracted from that segment. Comprehensive experimental results demonstrate that our method performs favorably against existing text-supervised semantic segmentation methods on six benchmark datasets.
title Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.04231