mlsanityData to 7 Oct 2026

Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks

arXiv 1912.09393 ↗First posted 19 Dec 2019cs.CV cs.LGcited by 112

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have improved image classification dramatically over the past decade, but have done so by focusing on performance measures that treat all classes other than the ground truth as equally wrong. This has led to a situation in which mistakes are less likely to be made than before, but are equally likely to be absurd or catastrophic when they do occur. Past works have recognised and tried to address this issue of mistake severity, often by using graph distances in class hierarchies, but this has largely been neglected since the advent of the current deep learning era in computer vision. In this paper, we aim to renew interest in this problem by reviewing past approaches and proposing two simple modifications of the cross-entropy loss which outperform the prior art under several metrics on two large datasets with complex class hierarchies: tieredImageNet and iNaturalist'19.

Key facts. Cited by 112 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 19; 2023: 16; 2024: 17; 2025: 22; 2026: 25.

112 papers.

Sort:

By area:

  1. 2023BioCLIP: A Vision Foundation Model for the Tree of Lifecited by 159
  2. 2022Deep Hierarchical Semantic Segmentationcited by 84
  3. 2022Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Frameworkcited by 59
  4. 2022Benchmarking Omni-Vision Representation through the Lens of Visual Realmscited by 38
  5. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  6. 2022Learning Hierarchy Aware Features for Reducing Mistake Severitycited by 26
  7. 2021No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networkscited by 21
  8. 2022Integrating Language Guidance into Vision-based Deep Metric Learningcited by 19
  9. 2022Skin Lesion Recognition with Class-Hierarchy Regularized Hyperbolic Embeddingscited by 19
  10. 2024Emergent Visual-Semantic Hierarchies in Image-Text Representationscited by 19
  11. 2023LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoningcited by 17
  12. 2024Visually Consistent Hierarchical Image Classificationcited by 16
38 more
  1. 2021Improving Dietary Assessment Via Integrated Hierarchy Food Classificationcited by 15
  2. 2022Hierarchical classification at multiple operating pointscited by 14
  3. 2021Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognitioncited by 13
  4. 2022Continual Learning with Evolving Class Ontologiescited by 13
  5. 2023Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severitycited by 13
  6. 2024LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomiescited by 12
  7. 2022Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networkscited by 11
  8. 2023Online Continual Learning on Hierarchical Label Expansioncited by 11
  9. 2024SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detectioncited by 11
  10. 2025Taxonomy-Aware Evaluation of Vision-Language Modelscited by 11
  11. 2023Revisiting Single-gated Mixtures of Expertscited by 10
  12. 2023Optimization of Rank Losses for Image Retrievalcited by 10
  13. 2023Deep Imbalanced Regression via Hierarchical Classification Adjustmentcited by 9
  14. 2024Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincar'e Ballcited by 9
  15. 2024HELM: Hierarchical Encoding for mRNA Language Modelingcited by 9
  16. 2022Multi-Granularity Regularized Re-Balancing for Class Incremental Learningcited by 8
  17. 2022Hierarchical Average Precision Training for Pertinent Image Retrievalcited by 8
  18. 2022Hierarchical Few-Shot Object Detection: Problem, Benchmark and Methodcited by 8
  19. 2025A Large and Balanced Corpus for Fine-grained Arabic Readability Assessmentcited by 8
  20. 2021HIERMATCH: Leveraging Label Hierarchies for Improving Semi-Supervised Learningcited by 7
  21. 2022A Survey of Neural Treescited by 7
  22. 2024Hierarchical Selective Classificationcited by 7
  23. 2024Revisiting Hierarchical Text Classification: Inference and Metricscited by 7
  24. 2021Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Imagescited by 6
  25. 2023SEAL: Simultaneous Label Hierarchy Exploration And Learningcited by 6
  26. 2021MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classificationcited by 5
  27. 2023Test-Time Amendment with a Coarse Classifier for Fine-Grained Classificationcited by 5
  28. 2024Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representationscited by 5
  29. 2022Prototype Based Classification from Hierarchy to Fairnesscited by 4
  30. 2023Reviving the Context: Camera Trap Species Classification as Link Prediction on Multimodal Knowledge Graphscited by 4
  31. 2025ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networkscited by 4
  32. 2025Continual Hyperbolic Learning of Instances and Classescited by 4
  33. 2021United We Learn Better: Harvesting Learning Improvements From Class Hierarchies Across Taskscited by 3
  34. 2021Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifierscited by 3
  35. 2021Encoding Hierarchical Information in Neural Networks helps in Subpopulation Shiftcited by 3
  36. 2022All Mistakes Are Not Equal: Comprehensive Hierarchy Aware Multi-label Predictions (CHAMP)cited by 3
  37. 2022Addressing Mistake Severity in Neural Networks with Semantic Knowledgecited by 3
  38. 2023Egocentric Hierarchical Visual Semanticscited by 3

50 most cited of 112 All 112 (JSON)