mlsanityData to 7 Oct 2026

Deep Layer Aggregation

arXiv 1707.06484 ↗First posted 20 Jul 2017cs.CV cs.LGcited by 436

Not on the map. Why?

Abstract (arXiv)

Visual recognition requires rich representations that span levels from low to high, scales from small to large, and resolutions from fine to coarse. Even with the depth of features in a convolutional network, a layer in isolation is not enough: compounding and aggregating these representations improves inference of what and where. Architectural efforts are exploring many dimensions for network backbones, designing deeper or wider architectures, but how to best aggregate layers and blocks across a network deserves further attention. Although skip connections have been incorporated to combine layers, these connections have been "shallow" themselves, and only fuse by simple, one-step operations. We augment standard architectures with deeper aggregation to better fuse information across layers. Our deep layer aggregation structures iteratively and hierarchically merge the feature hierarchy to make networks with better accuracy and fewer parameters. Experiments across architectures and tasks show that deep layer aggregation improves recognition and resolution compared to existing branching and merging schemes. The code is at https://github.com/ucbdrive/dla.

Key facts. Cited by 436 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 119; 2022: 105; 2023: 88; 2024: 63; 2025: 41; 2026: 20.

436 papers.

Sort:

By area:

  1. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  2. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  3. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  4. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  5. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  6. 2021An Empirical Study of Training End-to-End Vision-and-Language Transformerscited by 271
  7. 2022Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Mapscited by 255
  8. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  9. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 211
  10. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  11. 2021Multimodal Virtual Point 3D Detectioncited by 166
  12. 2022Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wildcited by 159
38 more
  1. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  2. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  3. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 155
  4. 2021Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networkscited by 141
  5. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 138
  6. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  7. 2021Probabilistic two-stage detectioncited by 130
  8. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  9. 2021Translating Images into Mapscited by 115
  10. 2022Global Tracking Transformerscited by 110
  11. 2022MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformercited by 108
  12. 2021Reformulating HOI Detection as Adaptive Set Predictioncited by 95
  13. 2022Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shiftcited by 94
  14. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 88
  15. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  16. 2021Geometry-based Distance Decomposition for Monocular 3D Object Detectioncited by 83
  17. 2021Crossover Learning for Fast Online Video Instance Segmentationcited by 83
  18. 2023SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detectioncited by 83
  19. 2021MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actionscited by 82
  20. 2022CLRNet: Cross Layer Refinement Network for Lane Detectioncited by 82
  21. 2021Monocular Quasi-Dense 3D Object Trackingcited by 80
  22. 2022Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Taskcited by 79
  23. 2025mHC: Manifold-Constrained Hyper-Connectionscited by 76
  24. 2021Large Scale Visual Food Recognitioncited by 75
  25. 2022The KFIoU Loss for Rotated Object Detectioncited by 73
  26. 2021HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPScited by 71
  27. 2021MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?cited by 68
  28. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  29. 2021Multiple Object Tracking with Correlation Learningcited by 67
  30. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 66
  31. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  32. 2022CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformercited by 66
  33. 2021SiamMOT: Siamese Multi-Object Trackingcited by 62
  34. 2021SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Watercited by 59
  35. 2021Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detectioncited by 58
  36. 2021No One Representation to Rule Them All: Overlapping Features of Training Methodscited by 57
  37. 2023Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Reviewcited by 57
  38. 2021DEFT: Detection Embeddings for Trackingcited by 56

50 most cited of 436 All 436 (JSON)