mlsanityData to 7 Oct 2026

The Self-Optimal-Transport Feature Transform

arXiv 2204.03065 ↗First posted 6 Apr 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

The Self-Optimal-Transport (SOT) feature transform is designed to upgrade the set of features of a data instance to facilitate downstream matching or grouping related tasks. The transformed set encodes a rich representation of high order relations between the instance features. Distances between transformed features capture their direct original similarity and their third party agreement regarding similarity to other features in the set. A particular min-cost-max-flow fractional matching problem, whose entropy regularized version can be approximated by an optimal transport (OT) optimization, results in our transductive transform which is efficient, differentiable, equivariant, parameterless and probabilistically interpretable. Empirically, the transform is highly effective and flexible in its use, consistently improving networks it is inserted into, in a variety of tasks and training schemes. We demonstrate its merits through the problem of unsupervised clustering and its efficiency and wide applicability for few-shot-classification, with state-of-the-art results, and large-scale person re-identification.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 35 of its 54 references that are in the map. First posted on arXiv 6 Apr 2022.

Builds on

35 of 54 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  8. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  9. 2016Matching Networks for One Shot Learningcited by 2,246
  10. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  11. 2017Deep Setscited by 1,394
  12. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
23 more
  1. 2021Transformers in Vision: A Surveycited by 1,009
  2. 2019A Closer Look at Few-shot Classificationcited by 679
  3. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 547
  4. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  5. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
  6. 2018Meta-learning with differentiable closed-form solverscited by 395
  7. 2020SCAN: Learning to Classify Images without Labelscited by 351
  8. 2017A simple neural network module for relational reasoningcited by 345
  9. 2019A Baseline for Few-Shot Image Classificationcited by 298
  10. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  11. 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 260
  12. 2019Style Transfer by Relaxed Optimal Transport and Self-Similaritycited by 167
  13. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
  14. 2018Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networkscited by 129
  15. 2020On Learning Sets of Symmetric Elementscited by 97
  16. 2020Laplacian Regularized Few-Shot Learningcited by 90
  17. 2021Relational Embedding for Few-Shot Classificationcited by 74
  18. 2020Leveraging the Feature Distribution in Transfer-based Few-Shot Learningcited by 72
  19. 2019Torchreid: A Library for Deep Learning Person Re-Identification in Pytorchcited by 41
  20. 2020Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-Identificationcited by 14
  21. 2021Few-Shot Learning by Integrating Spatial and Frequency Representationcited by 11
  22. 2020Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classificationcited by 7
  23. 2021Sill-Net: Feature Augmentation with Separated Illumination Representationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 1; 2024: 1; 2025: 0; 2026: 1.

7 papers.

  1. 2022Relative representations enable zero-shot latent space communicationcited by 175
  2. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  3. 2022Generalization in Neural Networks: A Broad Surveycited by 11
  4. 2024Making Large Vision Language Models to be Good Few-shot Learnerscited by 7
  5. 2022Class-Specific Channel Attention for Few-Shot Learningcited by 0
  6. 2023Few-shot Image Classification based on Gradual Machine Learningcited by 0
  7. 2026Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Associationcited by 0