mlsanityData to 14 Oct 2026

Multi-Scale Context Aggregation by Dilated Convolutions

arXiv 1511.07122 ↗First posted 23 Nov 2015cs.CVcited by 1,133

Not on the map. Why?

Abstract (arXiv)

State-of-the-art models for semantic segmentation are based on adaptations of convolutional networks that had originally been designed for image classification. However, dense prediction and image classification are structurally different. In this work, we develop a new convolutional network module that is specifically designed for dense prediction. The presented module uses dilated convolutions to systematically aggregate multi-scale contextual information without losing resolution. The architecture is based on the fact that dilated convolutions support exponential expansion of the receptive field without loss of resolution or coverage. We show that the presented context module increases the accuracy of state-of-the-art semantic segmentation systems. In addition, we examine the adaptation of image classification networks to dense prediction and show that simplifying the adapted network can increase accuracy.

Key facts. Cited by 1,133 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 2; 2019: 0; 2020: 0; 2021: 332; 2022: 255; 2023: 207; 2024: 152; 2025: 106; 2026: 79.

1,133 papers.

Sort:

By area:

  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  2. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  3. 2021Vision Transformers for Dense Predictioncited by 1,803
  4. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  5. 2024VMamba: Visual State Space Modelcited by 969
  6. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  7. 2021Multi-Stage Progressive Image Restorationcited by 816
  8. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  9. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  10. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  11. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 532
  12. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
38 more
  1. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  2. 2022Making the Most of Text Semantics to Improve Biomedical Vision--Language Processingcited by 339
  3. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
  4. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 280
  5. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  6. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  7. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 231
  8. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
  9. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  10. 2021CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentationcited by 227
  11. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  12. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  13. 2023PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solverscited by 216
  14. 2021MP3: A Unified Model to Map, Perceive, Predict and Plancited by 212
  15. 2022Visual Attention Networkcited by 210
  16. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  17. 2021UniT: Multimodal Multitask Learning with a Unified Transformercited by 195
  18. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  19. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  20. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 187
  21. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  22. 2021Conformer: Local Features Coupling Global Representations for Visual Recognitioncited by 164
  23. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 164
  24. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  25. 2022Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecastingcited by 151
  26. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  27. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  28. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mambacited by 146
  29. 2022Understanding The Robustness in Vision Transformerscited by 144
  30. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  31. 2023Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Surveycited by 140
  32. 2024Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentationcited by 133
  33. 2023Scalable Transformer for PDE Surrogate Modelingcited by 128
  34. 2021CycleMLP: A MLP-like Architecture for Dense Predictioncited by 126
  35. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  36. 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 123
  37. 2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
  38. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120

50 most cited of 1,133 All 1,133 (JSON)