mlsanityData to 14 Oct 2026

Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships

arXiv 2310.15999 ↗First posted 24 Oct 2023cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advances in fine-grained representation learning leverage local-to-global (emergent) relationships for achieving state-of-the-art results. The relational representations relied upon by such methods, however, are abstract. We aim to deconstruct this abstraction by expressing them as interpretable graphs over image views. We begin by theoretically showing that abstract relational representations are nothing but a way of recovering transitive relationships among local views. Based on this, we design Transitivity Recovering Decompositions (TRD), a graph-space search algorithm that identifies interpretable equivalents of abstract emergent relationships at both instance and class levels, and with no post-hoc computations. We additionally show that TRD is provably robust to noisy views, with empirical evidence also supporting this finding. The latter allows TRD to perform at par or even better than the state-of-the-art, while being fully interpretable. Implementation is available at https://github.com/abhrac/trd.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 59 of its 97 references that are in the map. First posted on arXiv 24 Oct 2023.

Builds on

59 of 97 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Graph Attention Networkscited by 8,923
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  5. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  6. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  8. 2019Relational Knowledge Distillationcited by 889
  9. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  10. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  11. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  12. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
38 more
  1. 2017A simple neural network module for relational reasoningcited by 346
  2. 2017Relation Networks for Object Detectioncited by 305
  3. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  4. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 239
  5. 2017No Fuss Distance Metric Learning using Proxiescited by 226
  6. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  7. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  8. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  9. 2020Learning Robust Representations via Multi-View Information Bottleneckcited by 191
  10. 2022Vision GNN: An Image is Worth Graph of Nodescited by 186
  11. 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
  12. 2021TransFG: A Transformer Architecture for Fine-grained Recognitioncited by 132
  13. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  14. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
  15. 2020GraphNorm: A Principled Approach to Accelerating Graph Neural Network Trainingcited by 117
  16. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  17. 2014Part-based R-CNNs for Fine-grained Category Detectioncited by 109
  18. 2020Interpretable and Accurate Fine-grained Recognition via Region Groupingcited by 75
  19. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  20. 2018Maximum-Entropy Fine-Grained Classificationcited by 65
  21. 2015Part-Stacked CNN for Fine-Grained Visual Categorizationcited by 62
  22. 2019Cross-X Learning for Fine-Grained Visual Categorizationcited by 61
  23. 2021Unsupervised Part Discovery from Contrastive Reconstructioncited by 57
  24. 2022Let Invariant Rationale Discovery Inspire Graph Contrastive Learningcited by 57
  25. 2014Making Risk Minimization Tolerant to Label Noisecited by 54
  26. 2019Learning Deep Bilinear Transformation for Fine-grained Image Representationcited by 54
  27. 2014Bird Species Categorization Using Pose Normalized Deep Convolutional Netscited by 50
  28. 2019Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networkscited by 49
  29. 2022Robust Contrastive Learning against Noisy Viewscited by 45
  30. 2016Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrievalcited by 44
  31. 2021Feature Fusion Vision Transformer for Fine-Grained Visual Categorizationcited by 40
  32. 2020Self-Supervised Relational Reasoning for Representation Learningcited by 37
  33. 2022Disentanglement of Correlated Factors via Hausdorff Factorized Supportcited by 37
  34. 2020Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxiescited by 36
  35. 2021Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classificationcited by 31
  36. 2015Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loopcited by 25
  37. 2020Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretabilitycited by 25
  38. 2022Fine-Grained Object Classification via Self-Supervised Pose Alignmentcited by 22

50 most cited of 59 All 59 (JSON)

Built on by

Not cited yet.