paper-with-me

홈 › Papers

Referring Image Segmentation via Recurrent Refinement Networks

2018-06-01 · CVPR 2018 6 · Ruiyu Li, Kaican Li, Yi-Chun Kuo, Michelle Shu, Xiaojuan Qi, Xiaoyong Shen, Jiaya Jia

We address the problem of image segmentation from natural language descriptions. Existing deep learning-based methods encode image representations based on the output of the last convolutional layer. One general issue is that the resulting image representation lacks multi-scale semantics, which are key components in advanced segmentation systems. In this paper, we utilize the feature pyramids inherently existing in convolutional neural networks to capture the semantics at different scales. To produce suitable information flow through the path of feature hierarchy, we propose Recurrent Refinement Network (RRN) that takes pyramidal features as input to refine the segmentation mask progressively. Experimental results on four available datasets show that our approach outperforms multiple baselines and state-of-the-art.

📄 PDF Abstract BibTeX

Code (1)

liruiyu/referseg_rrn tf

Tasks

Image SegmentationReferring Expression SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Recurrent Instance Segmentation using Sequences of Referring Expressions

2019-11-05 · Alba Herrera-Palacio, Carles Ventura, Carina Silberer, Ionut-Teodor Sorodoc 외

The goal of this work is to segment the objects in an image that are referred to by a sequence of linguistic descriptions (referring expressions). We propose a deep neural network with recurrent layers that output a sequ…

Instance SegmentationReferring ExpressionReferring Expression SegmentationSemantic Segmentation

Spatio-Semantic Expert Routing Architecture with Mixture-of-Experts for Referring Image Segmentation

2026-03-13 · Alaa Dalaq, Muzammil Behzad arxiv

Referring image segmentation aims to produce a pixel-level mask for the image region described by a natural-language expression. Although pretrained vision-language models have improved semantic grounding, many existing …

Computational EfficiencyImage Segmentation

See-Through-Text Grouping for Referring Image Segmentation

2019-10-01 · ICCV 2019 10 · Ding-Jie Chen, Songhao Jia, Yi-Chen Lo, Hwann-Tzong Chen 외

Motivated by the conventional grouping techniques to image segmentation, we develop their DNN counterpart to tackle the referring variant. The proposed method is driven by a convolutional-recurrent neural network (ConvRN…

Image Segmentationobject-detectionObject DetectionReferring Expression+4

CroBIM-U: Uncertainty-Driven Referring Remote Sensing Image Segmentation

2026-01-07 · Yuzhe Sun, Zhe Dong, Haochen Jiang, Tianzhu Liu 외 arxiv

Referring remote sensing image segmentation aims to localize specific targets described by natural language within complex overhead imagery. However, due to extreme scale variations, dense similar distractors, and intric…

Image Segmentation

Recurrent Multimodal Interaction for Referring Image Segmentation

2017-03-23 · ICCV 2017 10 · Chenxi Liu, Zhe Lin, Xiaohui Shen, Jimei Yang 외

In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independentl…

Image Segmentationmultimodal interactionSegmentationSemantic Segmentation