paper-with-me

Papers

Confidence Estimation Using Unlabeled Data

2023-07-19 · Chen Li, Xiaoling Hu, Chao Chen

Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this paper, we propose the first confidence estimation method for a semi-supervised setting, when most training labels are unavailable. We stipulate that even with limited training labels, we can still reasonably approximate the confidence of model on unlabeled samples by inspecting the prediction consistency through the training process. We use training consistency as a surrogate function and propose a consistency ranking loss for confidence estimation. On both image classification and segmentation tasks, our method achieves state-of-the-art performances in confidence estimation. Furthermore, we show the benefit of the proposed method through a downstream active learning task. The code is available at https://github.com/TopoXLab/consistency-ranking-loss

📄 PDF Abstract BibTeX arXiv:2307.10440

Code (1)

topoxlab/consistency-ranking-loss 공식 구현 pytorch

Tasks

Active Learningimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization

2020-12-01 · NeurIPS 2020 12 · Wei Wang, Min-Ling Zhang

Partial label learning assumes inaccurate supervision where each training example is associated with a set of candidate labels, among which only one is valid. In many real-world scenarios, however, it is costly and time-…

Partial Label Learningvalid

Pseudo-Loss Confidence Metric for Semi-Supervised Few-Shot Learning

2021-01-01 · ICCV 2021 10 · Kai Huang, Jie Geng, Wen Jiang, Xinyang Deng 외

Semi-supervised few-shot learning is developed to train a classifier that can adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data. Most semi-supervised few-shot learning methods select…

Few-Shot Learning

Importance Weight Estimation and Generalization in Domain Adaptation under Label Shift

2020-11-29 · Kamyar Azizzadenesheli

We study generalization under labeled shift for categorical and general normed label spaces. We propose a series of methods to estimate the importance weights from labeled source to unlabeled target domain and provide co…

Domain AdaptationGeneralization BoundsOperator learning

The Impact of Unlabeled Patterns in Rademacher Complexity Theory for Kernel Classifiers

2011-12-01 · NeurIPS 2011 12 · Luca Oneto, Davide Anguita, Alessandro Ghio, Sandro Ridella

We derive here new generalization bounds, based on Rademacher Complexity theory, for model selection and error estimation of linear (kernel) classifiers, which exploit the availability of unlabeled samples. In parti…

Generalization BoundsModel Selection

Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning

2021-11-16 · ACL ARR November 2021 11 · Anonymous

In this paper, we study the named entity recognition (NER) problem under distant supervision. Due to the incompleteness of the external dictionaries and/or knowledge bases, such distantly annotated training data usually …

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER