Data to 7 Oct 2026

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

arXiv 1802.02611 ↗First posted 7 Feb 2018cs.CVcited by 3,210

Not on the map. Why?

Cited by 54 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. We further explore the Xception model and apply the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and Cityscapes datasets, achieving the test set performance of 89.0% and 82.1% without any post-processing. Our paper is accompanied with a publicly available reference implementation of the proposed models in Tensorflow at urlhttps://github.com/tensorflow/models/tree/master/research/deeplab.

Key facts. Cited by 3,210 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 601; 2022: 610; 2023: 646; 2024: 540; 2025: 457; 2026: 356.

3,210 papers.

Sort:

By area:

2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
2022Visual Prompt Tuningcited by 1,674
2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
2021Segmenter: Transformer for Semantic Segmentationcited by 855
2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
2021Extract Free Dense Labels from CLIPcited by 580

38 more

2022Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPcited by 560
2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
2021Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysiscited by 418
2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 412
2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
2021Urban Radiance Fieldscited by 263
2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 259
2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 243
2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
2025Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcementcited by 234
2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 229
2024Sapiens: Foundation for Human Vision Modelscited by 229
2021CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentationcited by 227
2023Segment Anything in Medical Imagescited by 226
2023CLIP-Driven Universal Model for Organ Segmentation and Tumor Detectioncited by 224
2022CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusioncited by 222
2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
2021K-Net: Towards Unified Image Segmentationcited by 211
2022Visual Attention Networkcited by 210
2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
2022Knowledge Distillation from A Stronger Teachercited by 204
2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPcited by 199
2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
2021Decoupling Zero-Shot Semantic Segmentationcited by 198
2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
2021PandaSet: Advanced Sensor Suite Dataset for Autonomous Drivingcited by 186
2022Focal Modulation Networkscited by 186
2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 177
2022DaViT: Dual Attention Vision Transformerscited by 174

50 most cited of 3,210 All 3,210 (JSON)