Corpus ID: 18335574

Label Refinement Network for Coarse-to-Fine Semantic Segmentation

@article{Islam2017LabelRN,
  title={Label Refinement Network for Coarse-to-Fine Semantic Segmentation},
  author={Md. Amirul Islam and Shujon Naha and Mrigank Rochan and Neil D. B. Bruce and Yang Wang},
  journal={ArXiv},
  year={2017},
  volume={abs/1703.00551}
}
We consider the problem of semantic image segmentation using deep convolutional neural networks. We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at several resolutions. The segmentation labels at a coarse resolution are used together with convolutional features to obtain finer resolution segmentation labels. We define loss functions at several stages in the network to provide supervisions at different… Expand
Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling
TLDR
G-FRNet achieves state-of-the-art semantic segmentation results on the CamVid and Horse-Cow Parsing datasets and produces results competitive with the best performing approaches that appear in the literature for the other three datasets. Expand
Multi-path Fusion Network For Semantic Image Segmentation
TLDR
This paper proposes a deep neural network architecture, Multi-Path Fusion Network (MPFNet), for semantic image segmentation, which improves strong baselines built upon VGG16 on two urban scene datasets, CamVid and Cityscapes, which demonstrate its effectiveness in modeling context information. Expand
Semantic Segmentation with Labeling Uncertainty and Class Imbalance
TLDR
A new approach that calculates a weight for each pixel considering its class and uncertainty during the labeling process, which leads to significant improvements in three challenging segmentation tasks in comparison to baseline methods. Expand
Convolutional Networks with Bracket-Style Decoder for Semantic Scene Segmentation
TLDR
A deep convolutional network with bracket-style decoder, namely B-Net, is proposed to leverage the utilization of features learned at middle layers in the backbone networks (encoder) for constructing a final prediction map of densely enhanced semantic information. Expand
Gated Feedback Refinement Network for Dense Image Labeling
TLDR
This paper proposes Gated Feedback Refinement Network (G-FRNet), an end-to-end deep learning framework for dense labeling tasks that addresses this limitation of existing methods and introduces gate units that control the information passed forward in order to filter out ambiguity. Expand
Attention-Guided Label Refinement Network for Semantic Segmentation of Very High Resolution Aerial Orthoimages
  • Jianfeng Huang, Xinchang Zhang, Ying Sun, Q. Xin
  • Computer Science
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • 2021
TLDR
This article proposes an attention-guided label refinement network (ALRNet) for improved semantic labeling of VHR images that follows the paradigm of the encoder–decoder architecture, which progressively refines the coarse labeling maps of different scales by using the channelwise attention mechanism. Expand
Dense image labeling using deep learning
TLDR
End-toend encoder-decoder networks that initially make a coarse-grained prediction which is progressively refined to recover spatial details are proposed, that control information passed forward in order to resolve ambiguity. Expand
ResNet with Global and Local Image Features, Stacked Pooling Block, for Semantic Segmentation
TLDR
This paper implements a fusion layer that allows to merge global features and local features in encoder network and introduces a stacked pooling block, which is able to significantly expand the receptive fields of features maps and is essential to contextualize local semantic predictions. Expand
Fine Segmentation of Head and Torso Using Label Refinement Networks
This paper describes the application of an adaptation of the recently proposed Label Refinement Networks (LRN) for fine head and torso segmentation in unconstrained photographs of individuals. TheExpand
Learning deep representations for semantic image parsing: a comprehensive overview
TLDR
Three aspects of the progress of research on semantic image parsing are summarized, i.e., category-level semantic segmentation, instance-levelSemantic image parsing, and beyond segmentation. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 29 REFERENCES
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture
  • D. Eigen, R. Fergus
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutionalExpand
Feedforward semantic segmentation with zoom-out features
TLDR
This work introduces a purely feed-forward architecture for semantic segmentation that exploits statistical structure in the image and in the label space without setting up explicit structured prediction mechanisms, and thus avoids complex and expensive inference. Expand
Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
TLDR
A practical system which is able to predict pixel-wise class labels with a measure of model uncertainty, and shows that modelling uncertainty improves segmentation performance by 2-3% across a number of state of the art architectures such as SegNet, FCN and Dilation Network, with no additional parametrisation. Expand
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
TLDR
This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Expand
Learning Hierarchical Features for Scene Labeling
TLDR
A method that uses a multiscale convolutional network trained from raw pixels to extract dense feature vectors that encode regions of multiple sizes centered on each pixel, alleviates the need for engineered features, and produces a powerful representation that captures texture, shape, and contextual information. Expand
Hypercolumns for object segmentation and fine-grained localization
TLDR
Using hypercolumns as pixel descriptors, this work defines the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel, and shows results on three fine-grained localization tasks: simultaneous detection and segmentation, and keypoint localization. Expand
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
TLDR
Quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures, including FCN and DeconvNet. Expand
Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation
TLDR
This work introduces another model - dubbed Recombinator Networks - where coarse features inform finer features early in their formation such that finer features can make use of several layers of computation in deciding how to use coarse features. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
...
1
2
3
...