ﻻ يوجد ملخص باللغة العربية
We investigate learning a ConvNet classifier with class-imbalanced data. We found that a ConvNet significantly over-fits the minor classes that do not have sufficient training instances, which is quite opposite to a traditional machine learning model like logistic regression that often under-fits minor classes. We conduct a series of analysis and argue that feature deviation between the training and test instances serves as the main cause. We propose to incorporate class-dependent temperatures (CDT) in learning a ConvNet: CDT forces the minor-class instances to have larger decision values in the training phase, so as to compensate for the effect of feature deviation in the test data. We validate our approach on several benchmark datasets and achieve promising performance. We hope that our insights can inspire new ways of thinking in resolving class-imbalanced deep learning.
Neural networks trained with class-imbalanced data are known to perform poorly on minor classes of scarce training data. Several recent works attribute this to over-fitting to minor classes. In this paper, we provide a novel explanation of this issue
Data in real-world application often exhibit skewed class distribution which poses an intense challenge for machine learning. Conventional classification algorithms are not effective in the case of imbalanced data distribution, and may fail when the
Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the distribution di
Semi-Supervised Learning (SSL) has achieved great success in overcoming the difficulties of labeling and making full use of unlabeled data. However, SSL has a limited assumption that the numbers of samples in different classes are balanced, and many
We propose a novel unsupervised generative model that learns to disentangle object identity from other low-level aspects in class-imbalanced data. We first investigate the issues surrounding the assumptions about uniformity made by InfoGAN, and demon