DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs | VitaVision
PaperIEEE Transactions on Pattern Analysis and Machine Intelligence · 2018

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

Liang-Chieh ChenGeorge PapandreouIasonas KokkinosKevin MurphyAlan Yuille
arXiv 1606.00915DOIView in graph
1page built on it
4more pages cite it
2narratives
10registry papers cite it

In the Atlas

ModelPrimary source of
DeepLab

Dense semantic segmentation by repurposing an ImageNet classifier with atrous (dilated) convolution to preserve spatial resolution, an Atrous Spatial Pyramid Pooling head for multi-scale context, and a fully-connected CRF post-processor for boundary refinement — multi-year state of the art on PASCAL VOC 2012.

Cited as a reference by 4 pages, grouped by domain

Segmentation 3
PointRendRITMSegFormer
Features 1
MobileNetV3

Appears in 2 narratives

NarrativeSegmentation, from Energy to PromptNarrativeVision Under a Latency Budget

Lineage

Papers in the Atlas registry only · one dot per paper
Built upon by · 10
’15’16’17’18’19’20’21’22’23MobileNetV2: Inverted Residuals and Linear Bottlenecks (2018)BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation (2018)Momentum Contrast for Unsupervised Visual Representation Learning (2019)Searching for MobileNetV3 (2019)Fast-SCNN: Fast Semantic Segmentation Network (2019)PointRend: Image Segmentation As Rendering (2020)BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation (2020)Vision Transformers for Dense Prediction (2021)SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers (2021)Segment Anything (2023)Fully Convolutional Networks for Semantic Segmentation (2015)U-Net: Convolutional Networks for Biomedical Image Segmentation (2015)