paper-with-me

홈 › Papers

MSE Loss with Outlying Label for Imbalanced Classification

2021-07-06 · Sota Kato, Kazuhiro Hotta

In this paper, we propose mean squared error (MSE) loss with outlying label for class imbalanced classification. Cross entropy (CE) loss, which is widely used for image recognition, is learned so that the probability value of true class is closer to one by back propagation. However, for imbalanced datasets, the learning is insufficient for the classes with a small number of samples. Therefore, we propose a novel classification method using the MSE loss that can be learned the relationships of all classes no matter which image is input. Unlike CE loss, MSE loss is possible to equalize the number of back propagation for all classes and to learn the feature space considering the relationships between classes as metric learning. Furthermore, instead of the usual one-hot teacher label, we use a novel teacher label that takes the number of class samples into account. This induces the outlying label which depends on the number of samples in each class, and the class with a small number of samples has outlying margin in a feature space. It is possible to create the feature space for separating high-difficulty classes and low-difficulty classes. By the experiments on imbalanced classification and semantic segmentation, we confirmed that the proposed method was much improved in comparison with standard CE loss and conventional methods, even though only the loss and teacher labels were changed.

📄 PDF Abstract BibTeX arXiv:2107.02393

Code (0)

등록된 구현이 없습니다.

Tasks

Classificationimbalanced classificationMetric LearningSemantic Segmentation

Similar Papers 제목 키워드 기반

An Outlyingness Matrix for Multivariate Functional Data Classification

2017-04-09 · Wenlin Dai, Marc G. Genton

The classification of multivariate functional data is an important task in scientific research. Unlike point-wise data, functional data are usually classified by their shapes rather than by their scales. We define an out…

ClassificationGeneral Classificationspeech-recognitionSpeech Recognition

Imbalance-XGBoost: Leveraging Weighted and Focal Losses for Binary Label-Imbalanced Classification with XGBoost

2019-08-05 · Chen Wang, Chengyuan Deng, Suzhen Wang

The paper presents Imbalance-XGBoost, a Python package that combines the powerful XGBoost software with weighted and focal losses to tackle binary label-imbalanced classification tasks. Though a small-scale program in te…

Binary ClassificationClassificationGeneral Classificationimbalanced classification

Semi-supervised learning for medical image classification using imbalanced training data

2021-08-20 · Tri Huynh, Aiden Nibali, Zhen He

Medical image classification is often challenging for two reasons: a lack of labelled examples due to expensive and time-consuming annotation protocols, and imbalanced class labels due to the relative scarcity of disease…

image-classificationImage ClassificationMedical Image Classification

Regularized maximum correntropy machine

2015-01-18 · Jim Jing-Yan Wang, Yunji Wang, Bing-Yi Jing, Xin Gao

In this paper we investigate the usage of regularized correntropy framework for learning of classifiers from noisy labels. The class label predictors learned by minimizing transitional loss functions are sensitive to the…

Enhancement Encoding: A Novel Imbalanced Classification Approach via Encoding the Training Labels

2022-08-23 · Jia-Chen Zhao

Class imbalance, which is also called long-tailed distribution, is a common problem in classification tasks based on machine learning. If it happens, the minority data will be overwhelmed by the majority, which presents …

imbalanced classification