.png){kind=icon}
.png){kind=icon}
Return
Class-Imbalanced Deep Learning via a Class-Balanced Ensemble
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2021.3071122.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Class imbalance is a prevalent phenomenon in various real-world applications and it presents significant challenges to model learning, including deep learning. In this work, we embed ensemble learning into the deep convolutional neural networks (CNNs) to tackle the class-imbalanced learning problem. An ensemble of auxiliary classifiers branching out from various hidden layers of a CNN is trained together with the CNN in an end-to-end manner. To that end, we designed a new loss function that can rectify the bias toward the majority classes by forcing the CNN's hidden layers and its associated auxiliary classifiers to focus on the samples that have been misclassified by previous layers, thus enabling subsequent layers to develop diverse behavior and fix the errors of previous layers in a batch-wise manner. A unique feature of the new method is that the ensemble of auxiliary classifiers can work together with the main CNN to form a more powerful combined classifier, or can be removed after finished training the CNN and thus only acting the role of assisting class imbalance learning of the CNN to enhance the neural network's capability in dealing with class-imbalanced data. Comprehensive experiments are conducted on four benchmark data sets of increasing complexity (CIFAR-10, CIFAR-100, iNaturalist, and CelebA) and the results demonstrate significant performance improvements over the state-of-the-art deep imbalance learning methods.
Keywords:
Deep learning
Training
Task analysis
Data models
Computational modeling
Training data
Optimization
Class-imbalanced deep learning
class-balanced ensemble
deep convolutional neural network (CNN)
image classification
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W