Corpus ID: 102480348

GFF: Gated Fully Fusion for Semantic Segmentation

@article{Li2019GFFGF,
  title={GFF: Gated Fully Fusion for Semantic Segmentation},
  author={Xiangtai Li and Houlong Zhao and Lei Han and Yunhai Tong and Kuiyuan Yang},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.01803}
}
Semantic segmentation generates comprehensive understanding of scenes at a semantic level through densely predicting the category for each pixel. [...] Key Method Specifically, features at each level are enhanced by higher-level features with stronger semantics and lower-level features with more details, and gates are used to control the propagation of useful information which significantly reduces the noises during fusion. We achieve the state of the art results on two challenging scene understanding datasets…Expand
CARNet: Context Attention Refine Network for Semantic Segmentation
TLDR
This paper improves the quality of feature maps from two aspects: muti-level features fusion and global context encoding and presents a Gated Fuse Unit (GFU), proposed to aggregate context information. Expand
Learning More Accurate Features for Semantic Segmentation in CycleNet
TLDR
This paper proposes a new network – CycleNet, which considers assigning a more accurate representative for every pixel, and draws support from deformable convolution to select and recombine features from different blocks, thus improving the misalignment issues caused by simple interpolation. Expand
Dynamic Dual Sampling Module for Fine-Grained Semantic Segmentation
TLDR
A Dynamic Dual Sampling Module (DDSM) is proposed to conduct dynamic affinity modeling and propagate semantic context to local details, which yields a more discriminative representation. Expand
Bidirectional Pyramid Networks for Semantic Segmentation
TLDR
This work proposes to open up the backbone and design a simple yet effective multiscale network architecture, Bidirectional Pyramid Network (BPNet), and demonstrates the flexibility of BPNet on a prostate MRI segmentation task, achieving the state of the art with a 45x speed-up. Expand
Global Aggregation Then Local Distribution for Scene Parsing
  • Xiangtai Li, Li Zhang, +4 authors T. Xiang
  • Computer Science, Medicine
  • IEEE Transactions on Image Processing
  • 2021
TLDR
A novel local distribution module is designed which models the affinity map between global and local relationship for each pixel adaptively and can be modularized as an end-to-end trainable block and easily plugged into existing semantic segmentation networks, giving rise to the GALD networks. Expand
RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation
TLDR
The paper proposes a residual fusion block (RFB) to formulate the interdependencies of the encoders and presents the deep multimodal networks for RGB-D semantic segmentation called RFBNet, which achieved state-of-the-art performance. Expand
Deep multimodal fusion for semantic image segmentation: A survey
TLDR
The essential background concepts of deep multimodal fusion and the relevant applications in computer vision are described, aiming to provide the reader with a comprehensive and heuristic view of deep multi-modal image segmentation. Expand
AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing
TLDR
This paper proposes a new model, called Attention-Augmented Network (AttaNet), to capture both global context and multilevel semantics while keeping the efficiency high, and achieves different levels of speed/accuracy trade-offs on Cityscapes. Expand
GFNet: Gate Fusion Network With Res2Net for Detecting Salient Objects in RGB-D Images
TLDR
GFNet is evaluated using two popular RGB-D salient detection benchmark datasets and achieved state-of-the art performance. Expand
Scene Segmentation With Dual Relation-Aware Attention Network
TLDR
A Dual Relation-aware Attention Network (DRANet) is proposed to handle the task of scene segmentation and designs two types of compact attention modules, which model the contextual dependencies in spatial and channel dimensions, respectively. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 64 REFERENCES
ExFuse: Enhancing Feature Fusion for Semantic Segmentation
TLDR
A new framework, named ExFuse, is proposed to bridge the gap between low-level and high-level features and significantly improve the segmentation quality, which outperforms the previous state-of-the-art results. Expand
Multi-scale Context Intertwining for Semantic Segmentation
TLDR
This work proposes a novel scheme for aggregating features from different scales, which it refers to as Multi-Scale Context Intertwining (MSCI), which merge pairs of feature maps in a bidirectional and recurrent fashion, via connections between two LSTM chains. 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
DenseASPP for Semantic Segmentation in Street Scenes
TLDR
Densely connected Atrous Spatial Pyramid Pooling (DenseASPP) is proposed, which connects a set of atrous convolutional layers in a dense way, such that it generates multi-scale features that not only cover a larger scale range, but also cover that scale range densely, without significantly increasing the model size. 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
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. 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
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
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
Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation
TLDR
This work proposes a novel end-to-end trainable, deep, encoder-decoder architecture for single-pass semantic segmentation based on a cascaded architecture with feature-level long-range skip connections and introduces dense decoder shortcut connections. Expand
...
1
2
3
4
5
...