Semantic Binary Segmentation Using Convolutional Networks without Decoders

  title={Semantic Binary Segmentation Using Convolutional Networks without Decoders},
  author={Shubhra Aich and William van der Kamp and Ian Stavness},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
In this paper, we propose an efficient architecture for semantic image segmentation using the depth-to-space (D2S) operation. Our D2S model is comprised of a standard CNN encoder followed by a depth-to-space reordering of the final convolutional feature maps. Our approach eliminates the decoder portion of traditional encoder-decoder segmentation models and reduces the amount of computation almost by half. As a participant of the DeepGlobe Road Extraction competition, we evaluate our models on… 

Figures from this paper

DTS-Net: Depth-to-Space Networks for Fast and Accurate Semantic Object Segmentation
The proposed Depth-to-Space Net (DTS-Net), an effective technique for semantic segmentation using the efficient sub-pixel convolutional neural network, outperforms SOTA methods that depend on encoder–decoder architectures, although the implementation and computations are far simpler.
Bidirectional Attention Network for Monocular Depth Estimation
A Bidirectional Attention Network (BANet) is proposed, an end-to-end framework for monocular depth estimation (MDE) that addresses the limitation of effectively integrating local and global information in convolutional neural networks.
Road Extraction from Very High Resolution Images Using Weakly labeled OpenStreetMap Centerline
A novel weakly supervised method to extract road networks from VHR images using only the OSM (OpenStreetMap) road centerline as training data instead of high quality pixel-wise road width label is proposed.
Dense Refinement Residual Network for Road Extraction From Aerial Imagery Data
The proposed semantic segmentation architecture is composed of multiple DRR modules for the extraction of diversified roads alleviating the class imbalance problem and provides better results as compared to other recent architectures.
Fusing Classification and Segmentation DCNNs for Road Feature Mining on Aerial Images
By comparing two state-of-the-art baseline classification/segmentation DCNNs in several industrial application scenarios, it is illustrated that their relative performance may vary, leading to different choices.
RoadRouter: Multi-Task Learning of Road Network Extraction with Graph Representation
This work proposes the pixel-wise orientation CRF specific for bridging the fragmented road segments, and formalizes an image transformation protocol to parse the topology from the road segmentation.
LEOD-Net: Learning Line-Encoded Bounding Boxes for Real-Time Object Detection
The strength of the proposed method lies in its simplicity and ease of implementation unlike the recent state-of-the-art methods in object detection, which include complex processing pipelines.
Aerial Road Segmentation in the Presence of Topological Label Noise
This paper explores the training of custom U-Nets built with ResNet and DenseNet backbones using noise-aware losses that are robust towards label omission and registration noise and yields a consistent improvement in overall extraction quality and exhibit a strong capacity to cope with severe label noise.
RSNet: The Search for Remote Sensing Deep Neural Networks in Recognition Tasks
The experimental results obtained using four benchmark data sets for land-cover classification and scene classification tasks demonstrate that the searched RSNet can achieve a satisfactory accuracy with a high computational efficiency and provides an effective option for the processing of HRS imagery.
Fine-Grained Road Mining from Satellite Images with Bilateral Xception and DeepLab
  • Le-le Cao
  • Computer Science
    2019 International Joint Conference on Neural Networks (IJCNN)
  • 2019
A general fusion strategy is proposed that conveniently combines the strength of both classification and segmentation DCNNs using an end-to-end network architecture; this paradigm only requires pre-train segmentation/classificationDCNNs once, which then can be reused in different road feature mining tasks.


Learning Deconvolution Network for Semantic Segmentation
A novel semantic segmentation algorithm by learning a deep deconvolution network on top of the convolutional layers adopted from VGG 16-layer net, which demonstrates outstanding performance in PASCAL VOC 2012 dataset.
Fully Convolutional Networks for Semantic Segmentation
It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
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.
Rethinking Atrous Convolution for Semantic Image Segmentation
The proposed `DeepLabv3' system significantly improves over the previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.
Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network
This work proposes a Global Convolutional Network to address both the classification and localization issues for the semantic segmentation and suggests a residual-based boundary refinement to further refine the object boundaries.
Multi-Scale Context Aggregation by Dilated Convolutions
This work develops a new convolutional network module that is specifically designed for dense prediction, and shows that the presented context module increases the accuracy of state-of-the-art semantic segmentation systems.
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
RefineNet is presented, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections and introduces chained residual pooling, which captures rich background context in an efficient manner.
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
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).
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models.
Efficient object localization using Convolutional Networks
A novel architecture which includes an efficient `position refinement' model that is trained to estimate the joint offset location within a small region of the image to achieve improved accuracy in human joint location estimation is introduced.