# Towards Better Selective Classification

arXiv: https://arxiv.org/abs/2206.09034 · HTML: https://mlsanity.com/paper/2206.09034/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 17 Jun 2022.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [Revisiting the Calibration of Modern Neural Networks](https://mlsanity.com/paper/2106.07998/) (2021)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors](https://mlsanity.com/paper/2005.07186/) (2020)
- [Self-Adaptive Training: beyond Empirical Risk Minimization](https://mlsanity.com/paper/2002.10319/) (2020)
- [Deep Gamblers: Learning to Abstain with Portfolio Theory](https://mlsanity.com/paper/1907.00208/) (2019)
- [Classification with Rejection Based on Cost-sensitive Classification](https://mlsanity.com/paper/2010.11748/) (2020)
- [Selective Classification Can Magnify Disparities Across Groups](https://mlsanity.com/paper/2010.14134/) (2020)
- [The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods](https://mlsanity.com/paper/2203.02486/) (2022)
- [Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning](https://mlsanity.com/paper/2101.08732/) (2021)
- [Entropy Minimization vs. Diversity Maximization for Domain Adaptation](https://mlsanity.com/paper/2002.01690/) (2020)

## Built on by (most cited first, 25 of 25)

- [Overcoming Common Flaws in the Evaluation of Selective Classification Systems](https://mlsanity.com/paper/2407.01032/) (2024)
- [How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networks](https://mlsanity.com/paper/2305.15508/) (2023)
- [A Causal Framework for Evaluating Deferring Systems](https://mlsanity.com/paper/2405.18902/) (2024)
- [LOVM: Language-Only Vision Model Selection](https://mlsanity.com/paper/2306.08893/) (2023)
- [Selective Classification Under Distribution Shifts](https://mlsanity.com/paper/2405.05160/) (2024)
- [Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It](https://mlsanity.com/paper/2403.14715/) (2024)
- [Confidence-aware Contrastive Learning for Selective Classification](https://mlsanity.com/paper/2406.04745/) (2024)
- [Hierarchical Selective Classification](https://mlsanity.com/paper/2405.11533/) (2024)
- [Training Private Models That Know What They Don't Know](https://mlsanity.com/paper/2305.18393/) (2023)
- [Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones](https://mlsanity.com/paper/2412.19325/) (2024)
- [Rejection via Learning Density Ratios](https://mlsanity.com/paper/2405.18686/) (2024)
- [Deep Neural Networks Tend To Extrapolate Predictably](https://mlsanity.com/paper/2310.00873/) (2023)
- [Adaptive Confidence Regularization for Multimodal Failure Detection](https://mlsanity.com/paper/2603.02200/) (2026)
- [Loss-Controlling Calibration for Predictive Models](https://mlsanity.com/paper/2301.04378/) (2023)
- [Model Agnostic Explainable Selective Regression via Uncertainty Estimation](https://mlsanity.com/paper/2311.09145/) (2023)
- [Bounded-Abstention Pairwise Learning to Rank](https://mlsanity.com/paper/2505.23437/) (2025)
- [Know What You Don't Know: Selective Prediction for Early Exit DNNs](https://mlsanity.com/paper/2509.11520/) (2025)
- [Pseudo-D: Informing Multi-View Uncertainty Estimation with Calibrated Neural Training Dynamics](https://mlsanity.com/paper/2509.11800/) (2025)
- [Selective Prior Synchronization via SYNC Loss](https://mlsanity.com/paper/2602.11316/) (2026)
- [LogitDynamics: Reliable ViT Error Detection from Layerwise Logit Trajectories](https://mlsanity.com/paper/2604.10643/) (2026)
- [CHASE: Competing Hypotheses for Ambiguity-Aware Selective Prediction](https://mlsanity.com/paper/2605.01346/) (2026)
- [COVER: Learning to Accept More in Selective Sleep Staging](https://mlsanity.com/paper/2610.03911/) (2026)
- [Epistemic Uncertainty-Aware Defect Detection for Quality Control in Medical Device Manufacturing](https://mlsanity.com/paper/2610.09057/) (2026)
- [Strong yet Controllable LLM Abstention without Learning to Abstain](https://mlsanity.com/paper/2610.16318/) (2026)
- [Selective Next-Location Prediction with MetaModelSelect: A Lightweight Post-Hoc Confidence Metamodel](https://mlsanity.com/paper/2610.19394/) (2026)

## 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.