Multi-scale Context Intertwining for Semantic Segmentation

@inproceedings{Lin2018MultiscaleCI,
  title={Multi-scale Context Intertwining for Semantic Segmentation},
  author={Di Lin and Yuanfeng Ji and Dani Lischinski and D. Cohen-Or and Hui Huang},
  booktitle={ECCV},
  year={2018}
}
Accurate semantic image segmentation requires the joint consideration of local appearance, semantic information, and global scene context. In today’s age of pre-trained deep networks and their powerful convolutional features, state-of-the-art semantic segmentation approaches differ mostly in how they choose to combine together these different kinds of information. In this work, we propose a novel scheme for aggregating features from different scales, which we refer to as Multi-Scale Context… Expand
Dual Graph Convolutional Network for Semantic Segmentation
TLDR
The Dual Graph Convolutional Network (DGCNet) models the global context of the input feature by modelling two orthogonal graphs in a single framework, which achieves state-of-the-art results on both Cityscapes and Pascal Context datasets. Expand
Aggregating multi-scale contextual features from multiple stages for semantic image segmentation
Semantic segmentation plays a vital role in image understanding. Recent studies have attempted to achieve precise pixel-level classification by using deep networks that provide hierarchical features.Expand
Dynamic attention network for semantic segmentation
TLDR
This paper designs a Deformable Attention Pyramid module to perform a self-adjustable descriptor of high-level output, which utilizes deformable function to model geometric transformation and proposes a Fusing Attention Interim module to guide the back-propagation of long-short range information in each level of decoder. Expand
Dynamic Multi-Scale Filters for Semantic Segmentation
TLDR
A Dynamic Multi-scale Network (DMNet) is proposed to adaptively capture multi-scale contents for predicting pixel-level semantic labels and obtains state-of-the-art performance on Pascal-Context and ADE20K. Expand
Multi Receptive Field Network for Semantic Segmentation
TLDR
A new Multi-Receptive Field Module (MRFM) is proposed, explicitly taking multi-scale features into account, and an edge-aware loss is designed which is effective in distinguishing the boundaries of object/stuff. Expand
Dual Attention Network for Scene Segmentation
TLDR
New state-of-the-art segmentation performance on three challenging scene segmentation datasets, i.e., Cityscapes, PASCAL Context and COCO Stuff dataset is achieved without using coarse data. Expand
Gated Fully Fusion for Semantic Segmentation
TLDR
This paper proposes a new architecture, named Gated Fully Fusion(GFF), to selectively fuse features from multiple levels using gates in a fully connected way, and achieves the state of the art results on four challenging scene parsing datasets including Cityscapes, Pascal Context, COCO-stuff and ADE20K. Expand
GFF: Gated Fully Fusion for Semantic Segmentation
TLDR
This paper proposes a new architecture, named Gated Fully Fusion (GFF), to selectively fuse features from multiple levels using gates in a fully connected way, and achieves the state of the art results on four challenging scene parsing datasets. Expand
Adaptive Pyramid Context Network for Semantic Segmentation
TLDR
This paper introduces three desirable properties of context features in segmentation task and finds that Global-guided Local Affinity (GLA) can play a vital role in constructing effective context features, while this property has been largely ignored in previous works. Expand
Semantic Correlation Promoted Shape-Variant Context for Segmentation
TLDR
This work proposes a novel paired convolution to infer the semantic correlation of the pair and based on that to generate a shape mask, of which the receptive field is controlled by the shape mask that varies with the appearance of input. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 57 REFERENCES
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
Cascaded Feature Network for Semantic Segmentation of RGB-D Images
TLDR
This paper presents a neural network with multiple branches for segmenting RGB-D images, and introduces context-aware receptive field (CaRF) which provides a better control on the relevant contextual information of the learned features. 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
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. 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 Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF
TLDR
A structured patch prediction technique is introduced to make a trade-off between classification discriminability and boundary sensibility for features in a fast and accurate semantic image segmentation approach that encodes not only segmentation-specified features but also high-order context compatibilities and boundary guidance constraints. Expand
Semantic Object Parsing with Local-Global Long Short-Term Memory
TLDR
A novel deep Local-Global Long Short-Term Memory architecture to seamlessly incorporate short-distance and long-distance spatial dependencies into the feature learning over all pixel positions and demonstrates the significant superiority of this LG-LSTM over other state-of-the-art methods. Expand
Densely connected deconvolutional network for semantic segmentation
TLDR
This work proposes a Densely Connected Deconvolutional Network (DCDN) for semantic segmentation that achieves better performance than some state-of-the-art methods without using any post-processing, pretrained model, nor temporal information, whilst requiring less parameters. Expand
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
STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling
TLDR
A novel superpixel-based multi-view convolutional neural network for semantic image segmentation that produces a high quality segmentation of a single image by leveraging information from additional views of the same scene is proposed. Expand
...
1
2
3
4
5
...