• Corpus ID: 22655199

Rethinking Atrous Convolution for Semantic Image Segmentation

@article{Chen2017RethinkingAC,
  title={Rethinking Atrous Convolution for Semantic Image Segmentation},
  author={Liang-Chieh Chen and George Papandreou and Florian Schroff and Hartwig Adam},
  journal={ArXiv},
  year={2017},
  volume={abs/1706.05587}
}
In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment… 
View PDF on arXiv
View With Semantic Reader
3,708 Citations
Highly Influential Citations
605
Background Citations
1,173
Methods Citations
1,661
Results Citations
63

3,708 Citations

Citation Type

Citation Type

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
TLDR
This work extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries and applies the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network.
Multi-Receptive Atrous Convolutional Network for Semantic Segmentation
TLDR
This paper adapts the ResNet-101 model as the backbone network and proposes a MRACN segmentation model (MRACN-Seg), which captures the multi-receptive features and the global features at different receptive scales of the input.
GRANet: Global Refinement Atrous Convolutional Neural Network for Semantic Scene Segmentation
TLDR
This work proposes a global refinement atrous convolutional neural network (GRANet) for semantic scene segmentation, and proposes a multiple pooling module schemes to utilize the global context information to boost the performance of the GRANet.
Context Encoding for Semantic Segmentation
TLDR
The proposed Context Encoding Module significantly improves semantic segmentation results with only marginal extra computation cost over FCN, and can improve the feature representation of relatively shallow networks for the image classification on CIFAR-10 dataset.
Rethink Dilated Convolution for Real-time Semantic Segmentation
TLDR
This work designs a ResNeXt inspired block structure that uses two parallel 3 × 3 convolutional layers with different dilation rates to increase the field-of-view while also preserving the local details and proposes a lightweight decoder that restores local information better than common alternatives.
LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation
TLDR
A new deeper version of Atrous Spatial Pyramid Pooling module (ASPP) is explored and applied short and long residual connections, and depthwise separable convolution, resulting in a faster and efficient model for semantic image segmentation.
Partial Atrous Cascade R-CNN
TLDR
A novel instance segmentation framework named partial atrous cascade R-CNN (PAC), which effectively improves the accuracy of the segmentation boundary by expanding the receptive field of the convolutional layer, multi-scale semantic features are greatly enriched.
Segmenter: Transformer for Semantic Segmentation
TLDR
This paper introduces Segmenter, a transformer model for semantic segmentation that outperforms the state of the art on both ADE20K and Pascal Context datasets and is competitive on Cityscapes.
Image Semantic Segmentation Using Deep Convolutional Nets, Fully Connected Conditional Random Fields, and Dilated Convolution
  • Degui Xiao, P. Zhong
  • Computer Science
    2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)
  • 2019
TLDR
This work combines a new feature extraction network with a dilated convolution layer to improve the accuracy of the model's mission, and introduces multi-scale feature fusion technology to improved the performance of DCNN.
Multilevel feature fusion dilated convolutional network for semantic segmentation
TLDR
A multilevel feature fusion dilated convolution network (Refine-DeepLab) is proposed, which captures the rich context information and effectively alleviates the contradiction between the receptive field size and the dilated Convolution operation.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 98 REFERENCES
Understanding Convolution for Semantic Segmentation
TLDR
DUC is designed to generate pixel-level prediction, which is able to capture and decode more detailed information that is generally missing in bilinear upsampling, and a hybrid dilated convolution (HDC) framework in the encoding phase is proposed.
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TLDR
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.
Attention to Scale: Scale-Aware Semantic Image Segmentation
TLDR
An attention mechanism that learns to softly weight the multi-scale features at each pixel location is proposed, which not only outperforms averageand max-pooling, but allows us to diagnostically visualize the importance of features at different positions and scales.
Ladder-Style DenseNets for Semantic Segmentation of Large Natural Images
TLDR
A DenseNet-based ladder-style architecture is proposed which is able to deliver high modelling power with very lean representations at the original resolution, allow training at megapixel resolution on commodity hardware and display fair semantic segmentation performance even without ImageNet pre-training.
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
TLDR
This work shows how to improve semantic segmentation through the use of contextual information, specifically, ' patch-patch' context between image regions, and 'patch-background' context, and formulate Conditional Random Fields with CNN-based pairwise potential functions to capture semantic correlations between neighboring patches.
Stacked Deconvolutional Network for Semantic Segmentation
TLDR
This work proposes a Stacked Deconvolutional Network (SDN) for semantic segmentation and achieves the new state-ofthe- art results on four datasets, including PASCAL VOC 2012, CamVid, GATECH, COCO Stuff.
Convolutional feature masking for joint object and stuff segmentation
  • Jifeng Dai, Kaiming He, Jian Sun
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
TLDR
This paper proposes a joint method to handle objects and “stuff” (e.g., grass, sky, water) in the same framework and presents state-of-the-art results on benchmarks of PASCAL VOC and new PASCal-CONTEXT.
Fully Convolutional Networks for Semantic Segmentation
TLDR
It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.
Recurrent Scene Parsing with Perspective Understanding in the Loop
TLDR
This work proposes a depth-aware gating module that adaptively selects the pooling field size in a convolutional network architecture according to the object scale so that small details are preserved for distant objects while larger receptive fields are used for those nearby.
Scale-Adaptive Convolutions for Scene Parsing
TLDR
The proposed scale-adaptive convolutions are not only differentiable to learn the convolutional parameters and scale coefficients in an end-to-end way, but also of high parallelizability for the convenience of GPU implementation.
...
1
2
3
4
5
...