• Corpus ID: 237581618

PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation

@article{Daliparthi2021PDFNetPD,
  title={PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation},
  author={Venkata Satya Sai Ajay Daliparthi},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.10083}
}
In recent years, using a deep convolutional neural network (CNN) as a feature encoder (or backbone) is the most commonly observed architectural pattern in several computer vision methods, and semantic segmentation is no exception. The two major drawbacks of this architectural pattern are: (i) the networks often fail to capture small classes such as wall, fence, pole, traffic light, traffic sign, and bicycle, which are crucial for autonomous vehicles to make accurate decisions. (ii) due to the… 

References

SHOWING 1-10 OF 78 REFERENCES

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

The proposed DenseNets approach achieves state-of-the-art results on urban scene benchmark datasets such as CamVid and Gatech, without any further post-processing module nor pretraining, and has much less parameters than currently published best entries for these datasets.

CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning

Canet is presented, a class-agnostic segmentation network that performs few-shot segmentation on new classes with only a few annotated images available, and introduces an attention mechanism to effectively fuse information from multiple support examples under the setting of k-shot learning.

RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation

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.

RefineNet: Multi-Path Refinement Networks for Dense Prediction

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.

Stacked Deconvolutional Network for Semantic Segmentation

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.

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

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.

DenseASPP for Semantic Segmentation in Street Scenes

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.

HyperDense-Net: A Hyper-Densely Connected CNN for Multi-Modal Image Segmentation

HyperDenseNet is proposed, a 3-D fully convolutional neural network that extends the definition of dense connectivity to multi-modal segmentation problems and has total freedom to learn more complex combinations between the modalities, within and in-between all the levels of abstraction, which increases significantly the learning representation.

Ladder-Style DenseNets for Semantic Segmentation of Large Natural Images

A DenseNet-based ladder-style architecture is proposed which is able to deliver high modelling power with very lean representations at the original resolution, allow training at megapixel resolution on commodity hardware and display fair semantic segmentation performance even without ImageNet pre-training.

Fully convolutional networks for semantic segmentation

The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
...