mlsanityData to 7 Oct 2026

Towards Better Selective Classification

arXiv 2206.09034 ↗First posted 17 Jun 2022cs.LG cs.AI cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of Selective Classification where the objective is to achieve the best performance on a predetermined ratio (coverage) of the dataset. Recent state-of-the-art selective methods come with architectural changes either via introducing a separate selection head or an extra abstention logit. In this paper, we challenge the aforementioned methods. The results suggest that the superior performance of state-of-the-art methods is owed to training a more generalizable classifier rather than their proposed selection mechanisms. We argue that the best performing selection mechanism should instead be rooted in the classifier itself. Our proposed selection strategy uses the classification scores and achieves better results by a significant margin, consistently, across all coverages and all datasets, without any added compute cost. Furthermore, inspired by semi-supervised learning, we propose an entropy-based regularizer that improves the performance of selective classification methods. Our proposed selection mechanism with the proposed entropy-based regularizer achieves new state-of-the-art results.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 21 of its 36 references that are in the map. First posted on arXiv 17 Jun 2022.

Builds on

21 of 36 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2019Contrastive Multiview Codingcited by 1,297
  7. 2017Selective Classification for Deep Neural Networkscited by 799
  8. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  9. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  10. 2021Revisiting the Calibration of Modern Neural Networkscited by 387
  11. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  12. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
9 more
  1. 2020Consistent Estimators for Learning to Defer to an Expertcited by 262
  2. 2020Efficient and Scalable Bayesian Neural Nets with Rank-1 Factorscited by 171
  3. 2020Self-Adaptive Training: beyond Empirical Risk Minimizationcited by 126
  4. 2019Deep Gamblers: Learning to Abstain with Portfolio Theorycited by 69
  5. 2020Classification with Rejection Based on Cost-sensitive Classificationcited by 55
  6. 2020Selective Classification Can Magnify Disparities Across Groupscited by 35
  7. 2022The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methodscited by 28
  8. 2021Self-Adaptive Training: Bridging Supervised and Self-Supervised Learningcited by 17
  9. 2020Entropy Minimization vs. Diversity Maximization for Domain Adaptationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 8; 2025: 3; 2026: 4.

21 papers.

Sort:

By area:

  1. 2024Overcoming Common Flaws in the Evaluation of Selective Classification Systemscited by 31
  2. 2023How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networkscited by 15
  3. 2024A Causal Framework for Evaluating Deferring Systemscited by 13
  4. 2023LOVM: Language-Only Vision Model Selectioncited by 12
  5. 2024Selective Classification Under Distribution Shiftscited by 12
  6. 2024Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix Itcited by 11
  7. 2024Hierarchical Selective Classificationcited by 7
  8. 2024Confidence-aware Contrastive Learning for Selective Classificationcited by 7
  9. 2023Training Private Models That Know What They Don't Knowcited by 5
  10. 2024Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Onescited by 4
  11. 2024Rejection via Learning Density Ratioscited by 3
  12. 2023Deep Neural Networks Tend To Extrapolate Predictablycited by 1
9 more
  1. 2026Adaptive Confidence Regularization for Multimodal Failure Detectioncited by 1
  2. 2023Loss-Controlling Calibration for Predictive Modelscited by 0
  3. 2023Model Agnostic Explainable Selective Regression via Uncertainty Estimationcited by 0
  4. 2025Bounded-Abstention Pairwise Learning to Rankcited by 0
  5. 2025Know What You Don't Know: Selective Prediction for Early Exit DNNscited by 0
  6. 2025Pseudo-D: Informing Multi-View Uncertainty Estimation with Calibrated Neural Training Dynamicscited by 0
  7. 2026Selective Prior Synchronization via SYNC Losscited by 0
  8. 2026LogitDynamics: Reliable ViT Error Detection from Layerwise Logit Trajectoriescited by 0
  9. 2026CHASE: Competing Hypotheses for Ambiguity-Aware Selective Predictioncited by 0