mlsanityData to 7 Oct 2026

Deformable Convolutional Networks

arXiv 1703.06211 ↗First posted 17 Mar 2017cs.CVcited by 1,481

Not on the map. Why?

Cited by 26 in State-space sequence models (S4, Mamba), but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we introduce two new modules to enhance the transformation modeling capacity of CNNs, namely, deformable convolution and deformable RoI pooling. Both are based on the idea of augmenting the spatial sampling locations in the modules with additional offsets and learning the offsets from target tasks, without additional supervision. The new modules can readily replace their plain counterparts in existing CNNs and can be easily trained end-to-end by standard back-propagation, giving rise to deformable convolutional networks. Extensive experiments validate the effectiveness of our approach on sophisticated vision tasks of object detection and semantic segmentation. The code would be released.

Key facts. Cited by 1,481 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 311; 2022: 354; 2023: 299; 2024: 231; 2025: 187; 2026: 99.

1,481 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  3. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  4. 2021Transformers in Vision: A Surveycited by 1,009
  5. 2024VMamba: Visual State Space Modelcited by 955
  6. 2021Going deeper with Image Transformerscited by 759
  7. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  8. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  9. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  10. 2021Dynamic Neural Networks: A Surveycited by 405
  11. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  12. 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 340
38 more
  1. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  2. 2022Vision Transformer with Deformable Attentioncited by 293
  3. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  4. 2022Transformers in Medical Imaging: A Surveycited by 245
  5. 2022Neighborhood Attention Transformercited by 235
  6. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  7. 2021CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentationcited by 227
  8. 2021Co-Scale Conv-Attentional Image Transformerscited by 224
  9. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  10. 2022VRT: A Video Restoration Transformercited by 219
  11. 2021K-Net: Towards Unified Image Segmentationcited by 211
  12. 2022Visual Attention Networkcited by 210
  13. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  14. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 202
  15. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
  16. 2023ProPainter: Improving Propagation and Transformer for Video Inpaintingcited by 193
  17. 2022Towards Multi-spatiotemporal-scale Generalized PDE Modelingcited by 190
  18. 2022Medical Image Segmentation Review: The success of U-Netcited by 190
  19. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 185
  20. 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolationcited by 177
  21. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  22. 2021Multimodal Virtual Point 3D Detectioncited by 166
  23. 2021Conformer: Local Features Coupling Global Representations for Visual Recognitioncited by 164
  24. 2021Instances as Queriescited by 157
  25. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  26. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  27. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  28. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 155
  29. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  30. 2023BiFormer: Vision Transformer with Bi-Level Routing Attentioncited by 150
  31. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 149
  32. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  33. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  34. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  35. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  36. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 138
  37. 2021End-to-End Referring Video Object Segmentation with Multimodal Transformerscited by 135
  38. 2021OW-DETR: Open-world Detection Transformercited by 129

50 most cited of 1,481 All 1,481 (JSON)