DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

@article{Chen2018DeepLabSI,
  title={DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs},
  author={Liang-Chieh Chen and George Papandreou and Iasonas Kokkinos and Kevin P. Murphy and Alan Loddon Yuille},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2018},
  volume={40},
  pages={834-848}
}
In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. [...] Key Method Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks.Expand
Rethinking Atrous Convolution for Semantic Image Segmentation
TLDR
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. Expand
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. Expand
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. Expand
Atrous convolutional feature network for weakly supervised semantic segmentation
TLDR
This paper proposes an Atrous Convolutional Feature Network (ACFN) to generate dense object attention maps by enhancing the context representation of image classification CNNs, and proposes an attentive fusion strategy to adaptively fuse the multi-scale features. Expand
Optimized HRNet for image semantic segmentation
TLDR
An optimized high-resolution net (HRNet) for image semantic segmentation is proposed and a mixed dilated convolution (MDC) module is introduced, which can not only increase the diversity of the receptive fields, but also tackle the “gridding” problem commonly existing in the conventional dilated Convolution. Expand
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. Expand
Spatial Structure Preserving Feature Pyramid Network for Semantic Image Segmentation
TLDR
This work exploits the inherent multi-scale and pyramidal hierarchy of deep convolutional networks to extract the feature maps with different resolutions and take full advantages of these feature maps via a gradually stacked fusing way. Expand
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
TLDR
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. Expand
An end-to-end differential network learning method for semantic segmentation
TLDR
A novel differential network which addresses the small object segmentation and is superior to the state-of-the-art methods using only the primary segmentation model without applying a differential network. Expand
Progressively Diffused Networks for Semantic Image Segmentation
TLDR
The Progressively Diffused Networks framework demonstrates the effectiveness to substantially improve the performances over the popular existing neural network models, and achieves state-of-the-art on ImageNet Parsing for large scale semantic segmentation. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 111 REFERENCES
High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks
TLDR
A method for high-performance semantic image segmentation based on very deep residual networks, which achieves the state-of-the-art performance and demonstrates that online bootstrapping is critically important for achieving good accuracy. 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
Fast Semantic Image Segmentation with High Order Context and Guided Filtering
This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order contextExpand
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. Expand
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. Expand
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. Expand
Higher Order Conditional Random Fields in Deep Neural Networks
TLDR
Two types of higher order potentials, based on object detections and superpixels, can be included in a CRF embedded within a deep network to allow inference with the differentiable mean field algorithm and are designed to achieve state-of-the-art segmentation performance on the PASCAL VOC benchmark. Expand
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. Expand
Semantic Image Segmentation via Deep Parsing Network
TLDR
This paper addresses semantic image segmentation by incorporating rich information into Markov Random Field (MRF), including high-order relations and mixture of label contexts by proposing a Convolutional Neural Network (CNN), namely Deep Parsing Network (DPN), which enables deterministic end-to-end computation in a single forward pass. Expand
Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
TLDR
This work proposes replacing the fully-connected CRF with domain transform (DT), a modern edge-preserving filtering method in which the amount of smoothing is controlled by a reference edge map, and shows that it yields comparable semantic segmentation results, accurately capturing object boundaries. Expand
...
1
2
3
4
5
...