Augmentation by Counterfactual Explanation - Fixing an Overconfident Classifier.
Augmentation by Counterfactual Explanation - Fixing an Overconfident Classifier.
复制标题
DOI：
10.1109/wacv56688.2023.00470
复制
发表时间：
2023-01
期刊：
影响因子：
--
通讯作者：
Batmanghelich, Kayhan
中科院分区：
文献类型：
--
作者：
Singla, Sumedha;Murali, Nihal;Arabshahi, Forough;Triantafyllou, Sofia;Batmanghelich, Kayhan
高度准确但过于自信的模型不适合部署在医疗保健和自动驾驶等关键应用中。分类结果应反映出接近决策边界的模糊分布样本的高度不确定性。模型还应该避免对远离其训练分布的样本做出过度自信的决定，远离分布（far-out-of-distribution，far-OOD），或者对来自靠近其训练分布（near-OOD）的新类别的未知样本做出过度自信的决定。本文提出了反事实解释在确定一个过于自信的分类器中的应用。具体来说，我们建议使用反事实解释器（ACE）的增强来微调给定的预训练分类器，以修复其不确定性特征，同时保留其预测性能。我们进行了大量的实验，检测远OOD，近OOD，和模糊的样本。我们的实证结果表明，修改后的模型改进了不确定性度量，并且其性能与最先进的方法相竞争。
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.
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S
影响因子：
7.5
作者：
Huellermeier, Eyke;Waegeman, Willem
通讯作者：
Waegeman, Willem