Dual Convolutional LSTM Network for Referring Image Segmentation

被引:39
作者
Ye, Linwei [1 ]
Liu, Zhi [2 ,3 ]
Wang, Yang [1 ]
机构
[1] Univ Manitoba, Dept Comp Sci, Winnipeg, MB R3T 2N2, Canada
[2] Shanghai Univ, Shanghai Inst Adv Commun & Data Sci, Shanghai 200444, Peoples R China
[3] Shanghai Univ, Sch Commun & Informat Engn, Shanghai 200444, Peoples R China
基金
中国国家自然科学基金; 加拿大自然科学与工程研究理事会;
关键词
Image segmentation; Visualization; Decoding; Linguistics; Task analysis; Logic gates; Computer vision; Referring image segmentation; encoder-decoder; vision and language; deep learning;
D O I
10.1109/TMM.2020.2971171
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We consider referring image segmentation. It is a problem at the intersection of computer vision and natural language understanding. Given an input image and a referring expression in the form of a natural language sentence, the goal is to segment the object of interest in the image referred by the linguistic query. To this end, we propose a dual convolutional LSTM (ConvLSTM) network to tackle this problem. Our model consists of an encoder network and a decoder network, where ConvLSTM is used in both encoder and decoder networks to capture spatial and sequential information. The encoder network extracts visual and linguistic features for each word in the expression sentence, and adopts an attention mechanism to focus on words that are more informative in the multimodal interaction. The decoder network integrates the features generated by the encoder network at multiple levels as its input and produces the final precise segmentation mask. Experimental results on four challenging datasets demonstrate that the proposed network achieves superior segmentation performance compared with other state-of-the-art methods.
引用
收藏
页码:3224 / 3235
页数:12
相关论文
共 50 条
[31]   Learning From Box Annotations for Referring Image Segmentation [J].
Feng, Guang ;
Zhang, Lihe ;
Hu, Zhiwei ;
Lu, Huchuan .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (03) :3927-3937
[32]   Convolutional Neural Network Based Image Segmentation: A Review [J].
Ajmal, Hina ;
Rehman, Saad ;
Farooq, Umar ;
Ain, Qurrat U. ;
Riaz, Farhan ;
Hassan, Ali .
PATTERN RECOGNITION AND TRACKING XXIX, 2018, 10649
[33]   Morphable Convolutional Neural Network for Biomedical Image Segmentation [J].
Jiang, Huaipan ;
Sarma, Anup ;
Fan, Mengran ;
Ryoo, Jihyun ;
Arunachalam, Meenakshi ;
Naveen, Sharada ;
Kandemir, Mahmut T. .
PROCEEDINGS OF THE 2021 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE 2021), 2021, :1522-1525
[34]   Hierarchical collaboration for referring image segmentation [J].
Zhang, Wei ;
Cheng, Zesen ;
Chen, Jie ;
Gao, Wen .
NEUROCOMPUTING, 2025, 613
[35]   GENERATIVE ADVERSARIAL NETWORK INCLUDING REFERRING IMAGE SEGMENTATION FOR TEXT-GUIDED IMAGE MANIPULATION [J].
Watanabe, Yuto ;
Togo, Ren ;
Maeda, Keisuke ;
Ogawa, Takahiro ;
Haseyama, Miki .
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, :4818-4822
[36]   Two-stage Visual Cues Enhancement Network for Referring Image Segmentation [J].
Jiao, Yang ;
Jie, Zequn ;
Luo, Weixin ;
Chen, Jingjing ;
Jiang, Yu-Gang ;
Wei, Xiaolin ;
Ma, Lin .
PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, :1331-1340
[37]   SATR: Semantics-Aware Triadic Refinement network for referring image segmentation [J].
Xie, Jialong ;
Liu, Jin ;
Wang, Guoxiang ;
Zhou, Fengyu .
KNOWLEDGE-BASED SYSTEMS, 2024, 284
[38]   Prompt-guided bidirectional deep fusion network for referring image segmentation [J].
Wu, Junxian ;
Zhang, Yujia ;
Kampffmeyer, Michael ;
Zhao, Xiaoguang .
NEUROCOMPUTING, 2025, 616
[39]   Semantic Fire Segmentation Model Based on Convolutional Neural Network for Outdoor Image [J].
Choi, Han-Soo ;
Jeon, Myeongho ;
Song, Kyungmin ;
Kang, Myungjoo .
FIRE TECHNOLOGY, 2021, 57 (06) :3005-3019
[40]   Medical image segmentation algorithm based on feedback mechanism convolutional neural network [J].
An, Feng-Ping ;
Liu, Zhi-Wen .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2019, 53