Conservative Prediction via Data-Driven Confidence Minimization
- URL: http://arxiv.org/abs/2306.04974v2
- Date: Mon, 3 Jun 2024 13:30:28 GMT
- Title: Conservative Prediction via Data-Driven Confidence Minimization
- Authors: Caroline Choi, Fahim Tajwar, Yoonho Lee, Huaxiu Yao, Ananya Kumar, Chelsea Finn,
- Abstract summary: In safety-critical applications of machine learning, it is often desirable for a model to be conservative.
We propose the Data-Driven Confidence Minimization framework, which minimizes confidence on an uncertainty dataset.
- Score: 70.93946578046003
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In safety-critical applications of machine learning, it is often desirable for a model to be conservative, abstaining from making predictions on unknown inputs which are not well-represented in the training data. However, detecting unknown examples is challenging, as it is impossible to anticipate all potential inputs at test time. To address this, prior work (Hendrycks et al., 2018) minimizes model confidence on an auxiliary outlier dataset carefully curated to be disjoint from the training distribution. We theoretically analyze the choice of auxiliary dataset for confidence minimization, revealing two actionable insights: (1) if the auxiliary set contains unknown examples similar to those seen at test time, confidence minimization leads to provable detection of unknown test examples, and (2) if the first condition is satisfied, it is unnecessary to filter out known examples for out-of-distribution (OOD) detection. Motivated by these guidelines, we propose the Data-Driven Confidence Minimization (DCM) framework, which minimizes confidence on an uncertainty dataset. We apply DCM to two problem settings in which conservative prediction is paramount -- selective classification and OOD detection -- and provide a realistic way to gather uncertainty data for each setting. In our experiments, DCM consistently outperforms existing selective classification approaches on 4 datasets when tested on unseen distributions and outperforms state-of-the-art OOD detection methods on 12 ID-OOD dataset pairs, reducing FPR (at TPR $95\%$) by $6.3\%$ and $58.1\%$ on CIFAR-10 and CIFAR-100 compared to Outlier Exposure.
Related papers
- Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting [55.17761802332469]
Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and test data by adapting a given model w.r.t. any test sample.
Prior methods perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications.
We propose an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples.
arXiv Detail & Related papers (2024-03-18T05:49:45Z) - Revisiting Confidence Estimation: Towards Reliable Failure Prediction [53.79160907725975]
We find a general, widely existing but actually-neglected phenomenon that most confidence estimation methods are harmful for detecting misclassification errors.
We propose to enlarge the confidence gap by finding flat minima, which yields state-of-the-art failure prediction performance.
arXiv Detail & Related papers (2024-03-05T11:44:14Z) - Free Lunch for Generating Effective Outlier Supervision [46.37464572099351]
We propose an ultra-effective method to generate near-realistic outlier supervision.
Our proposed textttBayesAug significantly reduces the false positive rate over 12.50% compared with the previous schemes.
arXiv Detail & Related papers (2023-01-17T01:46:45Z) - Reliability-Aware Prediction via Uncertainty Learning for Person Image
Retrieval [51.83967175585896]
UAL aims at providing reliability-aware predictions by considering data uncertainty and model uncertainty simultaneously.
Data uncertainty captures the noise" inherent in the sample, while model uncertainty depicts the model's confidence in the sample's prediction.
arXiv Detail & Related papers (2022-10-24T17:53:20Z) - Augmenting Softmax Information for Selective Classification with
Out-of-Distribution Data [7.221206118679026]
We show that existing post-hoc methods perform quite differently compared to when evaluated only on OOD detection.
We propose a novel method for SCOD, Softmax Information Retaining Combination (SIRC), that augments softmax-based confidence scores with feature-agnostic information.
Experiments on a wide variety of ImageNet-scale datasets and convolutional neural network architectures show that SIRC is able to consistently match or outperform the baseline for SCOD.
arXiv Detail & Related papers (2022-07-15T14:39:57Z) - Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions.
In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data.
We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
arXiv Detail & Related papers (2022-01-11T23:01:12Z) - Gradient-based Novelty Detection Boosted by Self-supervised Binary
Classification [20.715158729811755]
Novelty detection aims to automatically identify out-of-distribution (OOD) data, without any prior knowledge of them.
We propose a novel, self-supervised approach that does not rely on any pre-defined OOD data.
In the evaluation with multiple datasets, the proposed approach consistently outperforms state-of-the-art supervised and unsupervised methods.
arXiv Detail & Related papers (2021-12-18T01:17:15Z) - Detecting Errors and Estimating Accuracy on Unlabeled Data with
Self-training Ensembles [38.23896575179384]
We propose a principled and practically effective framework that simultaneously addresses the two tasks.
One instantiation reduces the estimation error for unsupervised accuracy estimation by at least 70% and improves the F1 score for error detection by at least 4.7%.
On iWildCam, one instantiation reduces the estimation error for unsupervised accuracy estimation by at least 70% and improves the F1 score for error detection by at least 4.7%.
arXiv Detail & Related papers (2021-06-29T21:32:51Z) - Learn what you can't learn: Regularized Ensembles for Transductive
Out-of-distribution Detection [76.39067237772286]
We show that current out-of-distribution (OOD) detection algorithms for neural networks produce unsatisfactory results in a variety of OOD detection scenarios.
This paper studies how such "hard" OOD scenarios can benefit from adjusting the detection method after observing a batch of the test data.
We propose a novel method that uses an artificial labeling scheme for the test data and regularization to obtain ensembles of models that produce contradictory predictions only on the OOD samples in a test batch.
arXiv Detail & Related papers (2020-12-10T16:55:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.