Referring Image Segmentation via Recurrent Refinement Networks
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.
Code (1)
Tasks
Image SegmentationReferring Expression SegmentationSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Recurrent Instance Segmentation using Sequences of Referring Expressions
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 SegmentationSpatio-Semantic Expert Routing Architecture with Mixture-of-Experts for Referring Image Segmentation
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 SegmentationSee-Through-Text Grouping for Referring Image Segmentation
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+4CroBIM-U: Uncertainty-Driven Referring Remote Sensing Image Segmentation
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 SegmentationRecurrent Multimodal Interaction for Referring Image Segmentation
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