mlsanityData to 14 Oct 2026

On Hyperbolic Embeddings in 2D Object Detection

arXiv 2203.08049 ↗First posted 15 Mar 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Object detection, for the most part, has been formulated in the euclidean space, where euclidean or spherical geodesic distances measure the similarity of an image region to an object class prototype. In this work, we study whether a hyperbolic geometry better matches the underlying structure of the object classification space. We incorporate a hyperbolic classifier in two-stage, keypoint-based, and transformer-based object detection architectures and evaluate them on large-scale, long-tailed, and zero-shot object detection benchmarks. In our extensive experimental evaluations, we observe categorical class hierarchies emerging in the structure of the classification space, resulting in lower classification errors and boosting the overall object detection performance.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

37 of 46 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2020End-to-End Object Detection with Transformerscited by 7,414
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  9. 2018YOLOv3: An Incremental Improvementcited by 2,659
  10. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  11. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  12. 2019Objects as Pointscited by 1,175
25 more
  1. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 864
  2. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  3. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 684
  4. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 540
  5. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 495
  6. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 265
  7. 2019Hyperbolic Image Embeddingscited by 221
  8. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 201
  9. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 187
  10. 2021Probabilistic two-stage detectioncited by 130
  11. 2020TIDE: A General Toolbox for Identifying Object Detection Errorscited by 114
  12. 2020Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detectioncited by 99
  13. 2021EfficientLPS: Efficient LiDAR Panoptic Segmentationcited by 76
  14. 2020MOPT: Multi-Object Panoptic Trackingcited by 53
  15. 2019Spherical Text Embeddingcited by 49
  16. 2021Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Imagescited by 48
  17. 2021There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledgecited by 44
  18. 2021Zero-Shot Instance Segmentationcited by 40
  19. 2022Amodal Panoptic Segmentationcited by 38
  20. 2020Synthesizing the Unseen for Zero-shot Object Detectioncited by 32
  21. 2021Semantics-Guided Contrastive Network for Zero-Shot Object detectioncited by 26
  22. 2018Skip-gram word embeddings in hyperbolic spacecited by 20
  23. 2020Dynamic Object Removal and Spatio-Temporal RGB-D Inpainting via Geometry-Aware Adversarial Learningcited by 19
  24. 2018Gradient descent in hyperbolic spacecited by 11
  25. 2021Contrastive Object Detection Using Knowledge Graph Embeddingscited by 6

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3.

6 papers.

  1. 2023Poincar'e ResNetcited by 25
  2. 2023Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detectioncited by 15
  3. 2024Progressive Multi-Modal Fusion for Robust 3D Object Detectioncited by 11
  4. 2023Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequencescited by 9
  5. 2024Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World Perceptioncited by 8
  6. 2024A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasetscited by 4