• Corpus ID: 85542864

FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation

@article{Wu2019FastFCNRD,
  title={FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation},
  author={Huikai Wu and Junge Zhang and Kaiqi Huang and Kongming Liang and Yizhou Yu},
  journal={ArXiv},
  year={2019},
  volume={abs/1903.11816}
}
Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy computation complexity and memory footprint. [] Key Method With the proposed JPU, our method reduces the computation complexity by more than three times without performance loss. Experiments show that JPU is superior to other upsampling modules, which can be plugged into many existing approaches to reduce computation complexity and improve performance. By…
View PDF on arXiv
View With Semantic Reader
117 Citations
Highly Influential Citations
16
Background Citations
32
Methods Citations
44
Results Citations
1

117 Citations

Citation Type

Citation Type

EfficientFCN: Holistically-guided Decoding for Semantic Segmentation
TLDR
The EfficientFCN is proposed, whose backbone is a common ImageNet pre-trained network without any dilated convolution, and achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost.
PPANet: Point-Wise Pyramid Attention Network for Semantic Segmentation
TLDR
A combined loss function from dice loss and binary cross-entropy is developed to improve accuracy and get faster training convergence in KITTI road segmentation.
See More Than Once - Kernel-Sharing Atrous Convolution for Semantic Segmentation
Efficient Joined Pyramid Network Applied to Semantic Segmentation for GPU Embedded System
TLDR
According to the results, EJPNet not only has the best number of parameters, FLOPS, and time processing, but also this network has one of the best precisions and is a feasible semantic segmentation method for embedded systems applications.
Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task
TLDR
It is proposed that by sharing a common latent space, the complementary tasks can produce more robust representations that can enhance the semantic labels and demonstrate the effectiveness of learning in a multi-task setting for hourglass models in the Cityscapes, CamVid, and Freiburg Forest datasets by improving the state of the art without any refinement post-processing.
A Novel Upsampling and Context Convolution for Image Semantic Segmentation
TLDR
A novel dense upsampling convolution method based on a guided filter to effectively preserve the spatial information of the image in the network and a novel local context Convolution method that not only covers larger-scale objects in the scene but covers them densely for precise object boundary delineation.
A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection
TLDR
This paper proposes one novel holistically-guided decoder which is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder, and implements the EfficientFCN architecture for semantic segmentation and HGD-FPN for object detection and instance segmentation.
DCM: A Dense-Attention Context Module For Semantic Segmentation
TLDR
A new attention-augmented module named Dense-attention Context Module (DCM) is presented, which is used to connect the common backbones and the other decoding heads, which shows the promising results of this method on Cityscapes dataset.
Two-branch encoding and iterative attention decoding network for semantic segmentation
TLDR
This paper proposes a two-branch encoding and iterative attention decoding semantic segmentation model for deep convolutional neural networks and proposes a channel position attention module and a boundary residual attention module to learn different position and boundary features, which can enrich the target boundary position information.
Improving Semantic Segmentation via Self-Training
TLDR
This paper demonstrates the effectiveness of self-training on a challenging cross-domain generalization task, outperforming conventional finetuning method by a large margin and proposes a fast training schedule to accelerate the training of segmentation models by up to 2x without performance degradation.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 38 REFERENCES
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.
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.
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.
Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
TLDR
This work proposes a data-dependent upsampling (DUpsampling) to replace bilinear, which takes advantages of the redundancy in the label space of semantic segmentation and is able to recover the pixel-wise prediction from low-resolution outputs of CNNs.
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.
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.
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TLDR
This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models.
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.
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.
Multi-Scale Context Aggregation by Dilated Convolutions
TLDR
This work develops a new convolutional network module that is specifically designed for dense prediction, and shows that the presented context module increases the accuracy of state-of-the-art semantic segmentation systems.
...
1
2
3
4
...