Augmentation by Counterfactual Explanation -- Fixing an Overconfident Classifier
Not on the map. Why?
Abstract (arXiv)
A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples that lie close to the decision boundary. The model should also refrain from making overconfident decisions on samples that lie far outside its training distribution, far-out-of-distribution (far-OOD), or on unseen samples from novel classes that lie near its training distribution (near-OOD). This paper proposes an application of counterfactual explanations in fixing an over-confident classifier. Specifically, we propose to fine-tune a given pre-trained classifier using augmentations from a counterfactual explainer (ACE) to fix its uncertainty characteristics while retaining its predictive performance. We perform extensive experiments with detecting far-OOD, near-OOD, and ambiguous samples. Our empirical results show that the revised model have improved uncertainty measures, and its performance is competitive to the state-of-the-art methods.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 51 of its 76 references that are in the map. First posted on arXiv 21 Oct 2022.
Builds on
51 of 76 references.
References · 51
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2022Generative Adversarial Networkscited by 5,603
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2014Deep Learning Face Attributes in the Wildcited by 3,679
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
38 more
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2020Energy-based Out-of-distribution Detectioncited by 1,296
- 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
- 2018Deep Anomaly Detection with Outlier Exposurecited by 939
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
- 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
- 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
- 2018Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNscited by 585
- 2015Weight Uncertainty in Neural Networkscited by 554
- 2015Variational Dropout and the Local Reparameterization Trickcited by 489
- 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
- 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
- 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 428
- 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 426
- 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
- 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
- 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
- 2020Calibrating Deep Neural Networks using Focal Losscited by 353
- 2017Snapshot Ensembles: Train 1, get M for freecited by 349
- 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
- 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
- 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
- 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
- 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
- 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
- 2020Improving model calibration with accuracy versus uncertainty optimizationcited by 123
- 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
- 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
- 2021Can multi-label classification networks know what they don't know?cited by 100
- 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
- 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
- 2018Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detectioncited by 82
- 2019Explanation by Progressive Exaggerationcited by 76
- 2020Explaining The Efficacy of Counterfactually Augmented Datacited by 64
- 2019Out-of-Distribution Detection for Generalized Zero-Shot Action Recognitioncited by 54
50 most cited of 51 All 51 (JSON)
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.