Asymmetric Non-Local Neural Networks for Semantic Segmentation

@article{Zhu2019AsymmetricNN,
  title={Asymmetric Non-Local Neural Networks for Semantic Segmentation},
  author={Zhen Zhu and Mengde Xu and Song Bai and Tengteng Huang and Xiang Bai},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={593-602}
}
  • Zhen Zhu, Mengde Xu, X. Bai
  • Published 21 August 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
The non-local module works as a particularly useful technique for semantic segmentation while criticized for its prohibitive computation and GPU memory occupation. In this paper, we present Asymmetric Non-local Neural Network to semantic segmentation, which has two prominent components: Asymmetric Pyramid Non-local Block (APNB) and Asymmetric Fusion Non-local Block (AFNB). APNB leverages a pyramid sampling module into the non-local block to largely reduce the computation and memory consumption… 

CABiNet: Efficient Context Aggregation Network for Low-Latency Semantic Segmentation

TLDR
This paper proposes CABiNet (Context Aggregated Bi-lateral Network), a dual branch convolutional neural network (CNN), with significantly lower computational costs as compared to the state-of-the-art, while maintaining a competitive prediction accuracy.

Denoised Non-Local Neural Network for Semantic Segmentation

TLDR
This paper inventively proposes a Denoised NonLocal Network (Denoised NL), which consists of two primary modules, i.e., the Global Rectifying (GR) block and the Local Retention (LR) block, to eliminate the inter-class and intra-class noises respectively.

Real-time Semantic Segmentation with Context Aggregation Network

LRNNET: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation

TLDR
A light-weighted network with an efficient reduced non-local module (LRNNet) for efficient and realtime semantic segmentation and a factorized convolutional block in ResNet-Style encoder to achieve more lightweighted, efficient and powerful feature extraction.

Fully Attentional Network for Semantic Segmentation

TLDR
This work proposes a new approach, namely Fully Attentional Network (FLANet), to encode both spatial and channel attentions in a single similarity map while maintaining high computational efficiency.

Global Aggregation Then Local Distribution for Scene Parsing

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.

CAP: Context-Aware Pruning for Semantic Segmentation

TLDR
This paper advocates the importance of contextual information during channel pruning for semantic segmentation networks by presenting a novel Context-aware Pruning framework that reduces the number of parameters on PSPNet101, PSPNet50, ICNet, and SegNet, respectively, while preserving the performance.

Use square root affinity to regress labels in semantic segmentation

TLDR
This paper associates affinity matrix with labels, exploiting the affinity in a supervised way to generate a multi-scale label affinity matrix as a structural supervision, and defines a novel loss called Affinity Regression loss (AR loss), which can be an auxiliary loss providing pair-wise similarity penalty.

Lightweight Asymmetric Dilation Network for Real-Time Semantic Segmentation

TLDR
This work proposes a more comprehensive model that has not only a faster speed, but also a smaller number of parameters and a higher accuracy which is termed as Lightweight Asymmetric Dilation Network (LADNet).
...

References

SHOWING 1-10 OF 62 REFERENCES

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.

Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network

TLDR
This work proposes a Global Convolutional Network to address both the classification and localization issues for the semantic segmentation and suggests a residual-based boundary refinement to further refine the object boundaries.

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.

Non-local Neural Networks

TLDR
This paper presents non-local operations as a generic family of building blocks for capturing long-range dependencies in computer vision and improves object detection/segmentation and pose estimation on the COCO suite of tasks.

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.

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.

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.

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.

Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation

TLDR
A novel context contrasted local feature that not only leverages the informative context but also spotlights the local information in contrast to the context is proposed that greatly improves the parsing performance.

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.
...