mlsanityData to 7 Oct 2026

Contrastive Object Detection Using Knowledge Graph Embeddings

arXiv 2112.11366 ↗First posted 21 Dec 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Object recognition for the most part has been approached as a one-hot problem that treats classes to be discrete and unrelated. Each image region has to be assigned to one member of a set of objects, including a background class, disregarding any similarities in the object types. In this work, we compare the error statistics of the class embeddings learned from a one-hot approach with semantically structured embeddings from natural language processing or knowledge graphs that are widely applied in open world object detection. Extensive experimental results on multiple knowledge-embeddings as well as distance metrics indicate that knowledge-based class representations result in more semantically grounded misclassifications while performing on par compared to one-hot methods on the challenging COCO and Cityscapes object detection benchmarks. We generalize our findings to multiple object detection architectures by proposing a knowledge-embedded design for keypoint-based and transformer-based object detection architectures.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 37 of its 50 references that are in the map. First posted on arXiv 21 Dec 2021.

Builds on

37 of 50 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2017Mask R-CNNcited by 7,259
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  11. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  12. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
25 more
  1. 2019Objects as Pointscited by 1,172
  2. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  3. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  4. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  5. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  6. 2020Understanding the Behaviour of Contrastive Losscited by 397
  7. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  8. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  9. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  10. 2018Zero-Shot Object Detectioncited by 189
  11. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 185
  12. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  13. 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
  14. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  15. 2020Incremental Few-Shot Object Detectioncited by 102
  16. 2020Don't Judge an Object by Its Context: Learning to Overcome Contextual Biascited by 91
  17. 2021EfficientLPS: Efficient LiDAR Panoptic Segmentationcited by 76
  18. 2020Why Do Better Loss Functions Lead to Less Transferable Features?cited by 73
  19. 2019Adaptive NMS: Refining Pedestrian Detection in a Crowdcited by 66
  20. 2020MOPT: Multi-Object Panoptic Trackingcited by 53
  21. 2021Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Imagescited by 48
  22. 2018LinkNet: Relational Embedding for Scene Graphcited by 45
  23. 2021There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledgecited by 44
  24. 2019Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learningcited by 37
  25. 2020Background Learnable Cascade for Zero-Shot Object Detectioncited by 31

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 1; 2024: 1.

6 papers.

  1. 2022Understanding Masked Image Modeling via Learning Occlusion Invariant Featurecited by 50
  2. 2022ConQueR: Query Contrast Voxel-DETR for 3D Object Detectioncited by 21
  3. 2023Modeling Continuous Motion for 3D Point Cloud Object Trackingcited by 8
  4. 2022On Hyperbolic Embeddings in 2D Object Detectioncited by 6
  5. 2024Domain Adaptation for Large-Vocabulary Object Detectorscited by 2
  6. 2022Learning Self-Regularized Adversarial Views for Self-Supervised Vision Transformerscited by 1