paper-with-me

Papers

Selective Classification for Deep Neural Networks

2017-05-23 · NeurIPS 2017 12 · Yonatan Geifman, Ran El-Yaniv

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.

📄 PDF Abstract BibTeX arXiv:1705.08500

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral Classification

Similar Papers 제목 키워드 기반

Confidence-aware Contrastive Learning for Selective Classification

2024-06-07 · Yu-Chang Wu, Shen-Huan Lyu, Haopu Shang, Xiangyu Wang 외

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 Learning

Trading via Selective Classification

2021-10-28 · Nestoras Chalkidis, Rahul Savani

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 …

ClassificationPosition

Selective Classification Can Magnify Disparities Across Groups

2020-10-27 · ICLR 2021 1 · Erik Jones, Shiori Sagawa, Pang Wei Koh, Ananya Kumar 외

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 Classification

SelectiveNet: A Deep Neural Network with an Integrated Reject Option

2019-01-26 · Yonatan Geifman, Ran El-Yaniv

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 ClassificationPredictionregression

Hierarchical Selective Classification

2024-05-19 · Shani Goren, Ido Galil, Ran El-Yaniv

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