English
Related papers

Related papers: Instance-Level Costs for Nuanced Classifier Evalua…

200 papers

The problem of open-set noisy labels denotes that part of training data have a different label space that does not contain the true class. Lots of approaches, e.g., loss correction and label correction, cannot handle such open-set noisy…

Machine Learning · Computer Science 2021-06-02 Xiaobo Xia , Tongliang Liu , Bo Han , Mingming Gong , Jun Yu , Gang Niu , Masashi Sugiyama

While advanced classifiers have been increasingly used in real-world safety-critical applications, how to properly evaluate the black-box models given specific human values remains a concern in the community. Such human values include…

Machine Learning · Computer Science 2024-03-14 Yanyun Wang , Dehui Du , Yuanhao Liu

Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy,…

Computer Vision and Pattern Recognition · Computer Science 2020-09-10 Gongbo Liang , Yu Zhang , Xiaoqin Wang , Nathan Jacobs

Standard uncertainty estimation techniques, such as dropout, often struggle to clearly distinguish reliable predictions from unreliable ones. We attribute this limitation to noisy classifier weights, which, while not impairing overall…

Machine Learning · Computer Science 2025-06-09 Haripriya Harikumar , Santu Rana

The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated…

Machine Learning · Computer Science 2021-03-31 Zhaowei Zhu , Tongliang Liu , Yang Liu

Learning exists in the context of data, yet notions of confidence typically focus on model predictions, not label quality. Confident learning (CL) is an alternative approach which focuses instead on label quality by characterizing and…

Machine Learning · Statistics 2022-08-23 Curtis G. Northcutt , Lu Jiang , Isaac L. Chuang

There are many models, often called unnormalized models, whose normalizing constants are not calculated in closed form. Maximum likelihood estimation is not directly applicable to unnormalized models. Score matching, contrastive divergence…

Machine Learning · Statistics 2018-08-27 Masatoshi Uehara , Takeru Matsuda , Fumiyasu Komaki

Benchmarking models is a key factor for the rapid progress in machine learning (ML) research. Thus, further progress depends on improving benchmarking metrics. A standard metric to measure the behavioral alignment between ML models and…

Neurons and Cognition · Quantitative Biology 2025-11-10 Thomas Klein , Sascha Meyen , Wieland Brendel , Felix A. Wichmann , Kristof Meding

Noise plagues many numerical datasets, where the recorded values in the data may fail to match the true underlying values due to reasons including: erroneous sensors, data entry/processing mistakes, or imperfect human estimates. We consider…

Machine Learning · Statistics 2024-03-14 Hang Zhou , Jonas Mueller , Mayank Kumar , Jane-Ling Wang , Jing Lei

This paper tackles the problem of the worst-class error rate, instead of the standard error rate averaged over all classes. For example, a three-class classification task with class-wise error rates of 10%, 10%, and 40% has a worst-class…

Machine Learning · Statistics 2025-07-18 Yuya Saito , Shinnosuke Matsuo , Seiichi Uchida , Daiki Suehiro

Majorly classical Active Learning (AL) approach usually uses statistical theory such as entropy and margin to measure instance utility, however it fails to capture the data distribution information contained in the unlabeled data. This can…

Machine Learning · Computer Science 2020-12-10 Patrick K. Gikunda , Nicolas Jouandeau

Resource-constrained classification tasks are common in real-world applications such as allocating tests for disease diagnosis, hiring decisions when filling a limited number of positions, and defect detection in manufacturing settings…

Machine Learning · Computer Science 2023-11-22 Danit Shifman Abukasis , Izack Cohen , Xiaochen Xian , Kejun Huang , Gonen Singer

While deep neural networks have succeeded in several visual applications, such as object recognition, detection, and localization, by reaching very high classification accuracies, it is important to note that many real-world applications…

Computer Vision and Pattern Recognition · Computer Science 2020-10-06 Yu-An Chung , Shao-Wen Yang , Hsuan-Tien Lin

Everyone makes mistakes. So do human annotators when curating labels for named entity recognition (NER). Such label mistakes might hurt model training and interfere model comparison. In this study, we dive deep into one of the…

Computation and Language · Computer Science 2019-09-05 Zihan Wang , Jingbo Shang , Liyuan Liu , Lihao Lu , Jiacheng Liu , Jiawei Han

Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational…

Machine Learning · Computer Science 2025-10-30 Kuan Zhang , Chengliang Chai , Jingzhe Xu , Chi Zhang , Han Han , Ye Yuan , Guoren Wang , Lei Cao

Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in society at large. In this paper, we introduce a suite of…

Machine Learning · Computer Science 2019-05-09 Daniel Borkan , Lucas Dixon , Jeffrey Sorensen , Nithum Thain , Lucy Vasserman

Feature Selection is a crucial procedure in Data Science tasks such as Classification, since it identifies the relevant variables, making thus the classification procedures more interpretable, cheaper in terms of measurement and more…

Machine Learning · Statistics 2024-01-17 Sandra Benítez-Peña , Rafael Blanquero , Emilio Carrizosa , Pepa Ramírez-Cobo

Deep models trained with noisy labels are prone to over-fitting and struggle in generalization. Most existing solutions are based on an ideal assumption that the label noise is class-conditional, i.e., instances of the same class share the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-01 Ganlong Zhao , Guanbin Li , Yipeng Qin , Feng Liu , Yizhou Yu

Model efficiency is a critical aspect of developing and deploying machine learning models. Inference time and latency directly affect the user experience, and some applications have hard requirements. In addition to inference costs, model…

Machine Learning · Computer Science 2022-03-17 Mostafa Dehghani , Anurag Arnab , Lucas Beyer , Ashish Vaswani , Yi Tay

Some deep convolutional neural networks were proposed for time-series classification and class imbalanced problems. However, those models performed degraded and even failed to recognize the minority class of an imbalanced temporal sequences…

Machine Learning · Computer Science 2018-01-16 Yue Geng , Xinyu Luo