mlsanityData to 7 Oct 2026

Hierarchical Selective Classification

arXiv 2405.11533 ↗First posted 19 May 2024cs.LG cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical setting. Our approach leverages the inherent structure of class relationships, enabling models to reduce the specificity of their predictions when faced with uncertainty. In this paper, we first formalize hierarchical risk and coverage, and introduce hierarchical risk-coverage curves. Next, we develop algorithms for hierarchical selective classification (which we refer to as "inference rules"), and propose an efficient algorithm that guarantees a target accuracy constraint with high probability. Lastly, we conduct extensive empirical studies on over a thousand ImageNet classifiers, revealing that training regimes such as CLIP, pretraining on ImageNet21k and knowledge distillation boost hierarchical selective performance.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 42 of its 60 references that are in the map. First posted on arXiv 19 May 2024.

Builds on

42 of 60 references.

References · 42

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  5. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  6. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  7. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  8. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,163
  9. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  10. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  11. 2017Selective Classification for Deep Neural Networkscited by 799
  12. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
30 more
  1. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  2. 2021ImageNet-21K Pretraining for the Massescited by 607
  3. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  4. 2022DeiT III: Revenge of the ViTcited by 417
  5. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  6. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
  7. 2022Conformal Risk Controlcited by 290
  8. 2019Adversarial Examples Improve Image Recognitioncited by 283
  9. 2019Billion-scale semi-supervised learning for image classificationcited by 232
  10. 2021Benchmarking Representation Learning for Natural World Image Collectionscited by 167
  11. 2022MetaFormer Baselines for Visioncited by 131
  12. 2019Making Better Mistakes: Leveraging Class Hierarchies with Deep Networkscited by 112
  13. 2018Bias-Reduced Uncertainty Estimation for Deep Neural Classifierscited by 106
  14. 2020Individual Calibration with Randomized Forecastingcited by 50
  15. 2023What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifierscited by 35
  16. 2020Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifiercited by 34
  17. 2023Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstentioncited by 32
  18. 2022Calibrated Selective Classificationcited by 30
  19. 2024Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examplescited by 24
  20. 2023Towards Ontology Construction with Language Modelscited by 23
  21. 2020Constructing Taxonomies from Pretrained Language Modelscited by 21
  22. 2021No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networkscited by 21
  23. 2022Towards Better Selective Classificationcited by 21
  24. 2020Knapsack Pruning with Inner Distillationcited by 20
  25. 2023How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networkscited by 15
  26. 2022Hierarchical classification at multiple operating pointscited by 14
  27. 2024Multi-label Classification under Uncertainty: A Tree-based Conformal Prediction Approachcited by 7
  28. 2022Gumbel-Softmax Selective Networkscited by 1
  29. 2023On Calibration of Modern Quantized Efficient Neural Networkscited by 1
  30. 2023Eliciting Topic Hierarchies from Large Language Modelscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 4.

7 papers.

  1. 2024From Logits to Hierarchies: Hierarchical Clustering made Simplecited by 3
  2. 2025Conformal Prediction in Hierarchical Classification with Constrained Representation Complexitycited by 3
  3. 2026T-DuMpRa: Teacher-guided Dual-path Multi-prototype Retrieval Augmented framework for fine-grained medical image classificationcited by 1
  4. 2025Enhancing Conformal Prediction via Class Similaritycited by 0
  5. 2026The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?cited by 0
  6. 2026A Regime Theory of Controller Class Selection for LLM Action Decisionscited by 0
  7. 2026Multi-domain Multi-modal Document Classification Benchmark with a Multi-level Taxonomycited by 0