Selective Classification for Deep Neural Networks
Selective classification techniques (also known as reject option) have not yet been considered in the context of deep neural networks (DNNs). These techniques can potentially significantly improve DNNs prediction performance by trading-off coverage. In this paper we propose a method to construct a selective classifier given a trained neural network. Our method allows a user to set a desired risk level. At test time, the classifier rejects instances as needed, to grant the desired risk (with high probability). Empirical results over CIFAR and ImageNet convincingly demonstrate the viability of our method, which opens up possibilities to operate DNNs in mission-critical applications. For example, using our method an unprecedented 2% error in top-5 ImageNet classification can be guaranteed with probability 99.9%, and almost 60% test coverage.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationSimilar Papers 제목 키워드 기반
Confidence-aware Contrastive Learning for Selective Classification
Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use de…
ClassificationContrastive LearningTrading via Selective Classification
A binary classifier that tries to predict if the price of an asset will increase or decrease naturally gives rise to a trading strategy that follows the prediction and thus always has a position in the market. Selective …
ClassificationPositionSelective Classification Can Magnify Disparities Across Groups
Selective classification, in which models can abstain on uncertain predictions, is a natural approach to improving accuracy in settings where errors are costly but abstentions are manageable. In this paper, we find that …
ClassificationGeneral ClassificationSelectiveNet: A Deep Neural Network with an Integrated Reject Option
We consider the problem of selective prediction (also known as reject option) in deep neural networks, and introduce SelectiveNet, a deep neural architecture with an integrated reject option. Existing rejection mechanism…
ClassificationGeneral ClassificationPredictionregressionHierarchical Selective Classification
Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical …
ClassificationKnowledge DistillationSpecificity