mlsanityData to 14 Oct 2026

Unbalanced Optimal Transport: A Unified Framework for Object Detection

arXiv 2307.02402 ↗First posted 5 Jul 2023cs.CV cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

During training, supervised object detection tries to correctly match the predicted bounding boxes and associated classification scores to the ground truth. This is essential to determine which predictions are to be pushed towards which solutions, or to be discarded. Popular matching strategies include matching to the closest ground truth box (mostly used in combination with anchors), or matching via the Hungarian algorithm (mostly used in anchor-free methods). Each of these strategies comes with its own properties, underlying losses, and heuristics. We show how Unbalanced Optimal Transport unifies these different approaches and opens a whole continuum of methods in between. This allows for a finer selection of the desired properties. Experimentally, we show that training an object detection model with Unbalanced Optimal Transport is able to reach the state-of-the-art both in terms of Average Precision and Average Recall as well as to provide a faster initial convergence. The approach is well suited for GPU implementation, which proves to be an advantage for large-scale models.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 37 of its 66 references that are in the map. First posted on arXiv 5 Jul 2023.

Builds on

37 of 66 references.

References · 37

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2017Mask R-CNNcited by 7,277
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  10. 2015Fast R-CNNcited by 2,933
  11. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  12. 2017Improved Training of Wasserstein GANscited by 2,235
25 more
  1. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  2. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  3. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  4. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  5. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  6. 2018Computational Optimal Transportcited by 780
  7. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 720
  8. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 573
  9. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 488
  10. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  11. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  12. 2017Wasserstein Auto-Encoderscited by 373
  13. 2017Learning Generative Models with Sinkhorn Divergencescited by 314
  14. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  15. 2017Near-linear time approximation algorithms for optimal transport via Sinkhorn iterationcited by 223
  16. 2015Learning with a Wasserstein Losscited by 196
  17. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 178
  18. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  19. 2021Unbalanced minibatch Optimal Transport; applications to Domain Adaptationcited by 125
  20. 2016Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problemscited by 73
  21. 2015Sliced Wasserstein Kernels for Probability Distributionscited by 65
  22. 2018On the Latent Space of Wasserstein Auto-Encoderscited by 22
  23. 2019Screening Sinkhorn Algorithm for Regularized Optimal Transportcited by 20
  24. 2022Optimal Correction Cost for Object Detection Evaluationcited by 11
  25. 2020Wasserstein Exponential Kernelscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 9.

15 papers.

Sort:

By area:

  1. 2024Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentationcited by 38
  2. 2024AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportationcited by 28
  3. 2025Joint Self-Supervised Video Alignment and Action Segmentationcited by 11
  4. 2024Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Losscited by 7
  5. 2026Bridging Vision and Language Concepts through Optimal Transport Semantic Flowcited by 1
  6. 2026Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approachcited by 1
  7. 2025Gromov-Wasserstein and optimal transport: from assignment problems to probabilistic numericcited by 0
  8. 2025Optimal Transport for Handwritten Text Recognition in a Low-Resource Regimecited by 0
  9. 2026Accelerated Sinkhorn Algorithms for Partial Optimal Transportcited by 0
  10. 2026Gromov Wasserstein Optimal Transport for Semantic Correspondencescited by 0
  11. 2026Unbalanced optimal transport for robust longitudinal lesion evolution with registration-aware and appearance-guided priorscited by 0
  12. 2026Noise-aware few-shot learning through bi-directional multi-view prompt alignmentcited by 0
3 more
  1. 2026Telescope: Learnable Hyperbolic Foveation for Ultra-Long-Range Object Detectioncited by 0
  2. 2026OTCHA: Optimal Transport-driven Confidence-aware Latent Hub Alignment for Multi-View Medical Image Classificationcited by 0
  3. 2026Quantifying Annotation Agreement in Object Detection with Optimal Transportcited by 0