mlsanityData to 7 Oct 2026

HR-RCNN: Hierarchical Relational Reasoning for Object Detection

arXiv 2110.13892 ↗First posted 26 Oct 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Incorporating relational reasoning in neural networks for object recognition remains an open problem. Although many attempts have been made for relational reasoning, they generally only consider a single type of relationship. For example, pixel relations through self-attention (e.g., non-local networks), scale relations through feature fusion (e.g., feature pyramid networks), or object relations through graph convolutions (e.g., reasoning-RCNN). Little attention has been given to more generalized frameworks that can reason across these relationships. In this paper, we propose a hierarchical relational reasoning framework (HR-RCNN) for object detection, which utilizes a novel graph attention module (GAM). This GAM is a concise module that enables reasoning across heterogeneous nodes by operating on the graph edges directly. Leveraging heterogeneous relationships, our HR-RCNN shows great improvement on COCO dataset, for both object detection and instance segmentation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 73 of its 86 references that are in the map. First posted on arXiv 26 Oct 2021.

Builds on

73 of 86 references.

References · 73

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2017Graph Attention Networkscited by 8,854
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2017Mask R-CNNcited by 7,259
  9. 2017Inductive Representation Learning on Large Graphscited by 6,284
  10. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  11. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  12. 2017Non-local Neural Networkscited by 2,290
38 more
  1. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  2. 2017Deformable Convolutional Networkscited by 1,481
  3. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  4. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  5. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  7. 2018Path Aggregation Network for Instance Segmentationcited by 796
  8. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  9. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  10. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  11. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 557
  12. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  13. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  14. 2017Deep Layer Aggregationcited by 436
  15. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
  16. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  17. 2017Relation Networks for Object Detectioncited by 305
  18. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  19. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  20. 2018Graph networks as learnable physics engines for inference and controlcited by 242
  21. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  22. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  23. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  24. 2015Conditional Random Fields as Recurrent Neural Networkscited by 213
  25. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  26. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 200
  27. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 185
  28. 2019Scale-Aware Trident Networks for Object Detectioncited by 159
  29. 2020Probabilistic Anchor Assignment with IoU Prediction for Object Detectioncited by 150
  30. 2017DSSD : Deconvolutional Single Shot Detectorcited by 130
  31. 2014Hypercolumns for Object Segmentation and Fine-grained Localizationcited by 128
  32. 2017An Analysis of Scale Invariance in Object Detection - SNIPcited by 119
  33. 2019Relation-Aware Graph Attention Network for Visual Question Answeringcited by 119
  34. 2019Dynamic Graph Attention for Referring Expression Comprehensioncited by 111
  35. 2020Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Trainingcited by 103
  36. 2017Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approachcited by 102
  37. 2019Scene Graph Generation with External Knowledge and Image Reconstructioncited by 102
  38. 2018SNIPER: Efficient Multi-Scale Trainingcited by 87

50 most cited of 73 All 73 (JSON)

Built on by

Not cited yet.