mlsanityData to 7 Oct 2026

The Balanced-Pairwise-Affinities Feature Transform

arXiv 2407.01467 ↗First posted 25 Jun 2024cs.LG cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

The Balanced-Pairwise-Affinities (BPA) feature transform is designed to upgrade the features of a set of input items to facilitate downstream matching or grouping related tasks. The transformed set encodes a rich representation of high order relations between the input features. A particular min-cost-max-flow fractional matching problem, whose entropy regularized version can be approximated by an optimal transport (OT) optimization, leads to a transform which is efficient, differentiable, equivariant, parameterless and probabilistically interpretable. While the Sinkhorn OT solver has been adapted extensively in many contexts, we use it differently by minimizing the cost between a set of features to itself and using the transport plan's rows as the new representation. Empirically, the transform is highly effective and flexible in its use and consistently improves networks it is inserted into, in a variety of tasks and training schemes. We demonstrate state-of-the-art results in few-shot classification, unsupervised image clustering and person re-identification. Code is available at urlgithub.com/DanielShalam/BPA.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 37 of its 58 references that are in the map. First posted on arXiv 25 Jun 2024.

Builds on

37 of 58 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  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. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  11. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  12. 2017Deep Setscited by 1,394
25 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. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  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. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 292
  12. 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 260
  13. 2019Style Transfer by Relaxed Optimal Transport and Self-Similaritycited by 167
  14. 2021Sinkformers: Transformers with Doubly Stochastic Attentioncited by 136
  15. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  16. 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
  17. 2019Learning Combinatorial Embedding Networks for Deep Graph Matchingcited by 98
  18. 2020On Learning Sets of Symmetric Elementscited by 97
  19. 2020Laplacian Regularized Few-Shot Learningcited by 90
  20. 2020Deep Graph Matching Consensuscited by 85
  21. 2021Relational Embedding for Few-Shot Classificationcited by 74
  22. 2020Leveraging the Feature Distribution in Transfer-based Few-Shot Learningcited by 72
  23. 2020Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-Identificationcited by 14
  24. 2021Few-Shot Learning by Integrating Spatial and Frequency Representationcited by 11
  25. 2021Sill-Net: Feature Augmentation with Separated Illumination Representationcited by 7

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025RoNFA: Robust Neural Field-based Approach for Few-Shot Image Classification with Noisy Labelscited by 0
  2. 2025ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluationcited by 0