• Corpus ID: 239998498

Denoised Non-Local Neural Network for Semantic Segmentation

@article{Song2021DenoisedNN,
  title={Denoised Non-Local Neural Network for Semantic Segmentation},
  author={Qi Song and Jie Li and Hao Guo and Rui Huang},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.14200}
}
  • Qi Song, Jie Li, +1 author Rui Huang
  • Published 27 October 2021
  • Computer Science
  • ArXiv
The non-local network has become a widely used technique for semantic segmentation, which computes an attention map to measure the relationships of each pixel pair. However, most of the current popular non-local models tend to ignore the phenomenon that the calculated attention map appears to be very noisy, containing inter-class and intra-class inconsistencies, which lowers the accuracy and reliability of the non-local methods. In this paper, we figuratively denote these inconsistencies as… 

References

SHOWING 1-10 OF 63 REFERENCES
Asymmetric Non-Local Neural Networks for Semantic Segmentation
TLDR
Asymmetric Pyramid Non- local Block (APNB) and Asymmetric Fusion Non-local Block (AFNB) are presented, which has two prominent components: APNB leverages a pyramid sampling module into the non-local block to largely reduce the computation and memory consumption without sacrificing the performance.
ACFNet: Attentional Class Feature Network for Semantic Segmentation
  • Fan Zhang, Yanqin Chen, +5 authors Errui Ding
  • Computer Science
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
TLDR
This paper presents the concept of class center which extracts the global context from a categorical perspective, and proposes a novel module, named Attentional Class Feature (ACF) module, to calculate and adaptively combine different class centers according to each pixel.
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.
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.
Learning a Discriminative Feature Network for Semantic Segmentation
TLDR
This work proposes a Discriminative Feature Network (DFN), which contains two sub-networks: Smooth Network and Border Network, which is specially design to handle the intra-class inconsistency problem and to make the bilateral features of boundary distinguishable with deep semantic boundary supervision.
CCNet: Criss-Cross Attention for Semantic Segmentation
TLDR
This work proposes a Criss-Cross Network (CCNet) for obtaining contextual information in a more effective and efficient way and achieves the mIoU score of 81.4 and 45.22 on Cityscapes test set and ADE20K validation set, respectively, which are the new state-of-the-art results.
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.
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
TLDR
A novel Bilateral Segmentation Network (BiSeNet) is proposed that makes a right balance between the speed and segmentation performance on Cityscapes, CamVid, and COCO-Stuff datasets.
Adaptive Context Network for Scene Parsing
  • J. Fu, Jiange Liu, +4 authors Hanqing Lu
  • Computer Science
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
TLDR
This paper proposes an Adaptive Context Network (ACNet) to capture the pixel-aware contexts by a competitive fusion of global context and local context according to different per-pixel demands.
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.
...
1
2
3
4
5
...