Max-margin Class Imbalanced Learning with Gaussian Affinity
Real-world object classes appear in imbalanced ratios. This poses a significant challenge for classifiers which get biased towards frequent classes. We hypothesize that improving the generalization capability of a classifier should improve learning on imbalanced datasets. Here, we introduce the first hybrid loss function that jointly performs classification and clustering in a single formulation. Our approach is based on an `affinity measure' in Euclidean space that leads to the following benefits: (1) direct enforcement of maximum margin constraints on classification boundaries, (2) a tractable way to ensure uniformly spaced and equidistant cluster centers, (3) flexibility to learn multiple class prototypes to support diversity and discriminability in feature space. Our extensive experiments demonstrate the significant performance improvements on visual classification and verification tasks on multiple imbalanced datasets. The proposed loss can easily be plugged in any deep architecture as a differentiable block and demonstrates robustness against different levels of data imbalance and corrupted labels.
Code (1)
Tasks
ClassificationClusteringDiversityGeneral ClassificationSimilar Papers 제목 키워드 기반
Gaussian Affinity for Max-Margin Class Imbalanced Learning
Real-world object classes appear in imbalanced ratios. This poses a significant challenge for classifiers which get biased towards frequent classes. We hypothesize that improving the generalization capability of a class…
ClassificationClusteringDiversityGeneral ClassificationDA-PFL: Dynamic Affinity Aggregation for Personalized Federated Learning
Personalized federated learning becomes a hot research topic that can learn a personalized learning model for each client. Existing personalized federated learning models prefer to aggregate similar clients with similar …
Federated LearningPersonalized Federated LearningEnlarged Large Margin Loss for Imbalanced Classification
We propose a novel loss function for imbalanced classification. LDAM loss, which minimizes a margin-based generalization bound, is widely utilized for class-imbalanced image classification. Although, by using LDAM loss, …
Classificationimage-classificationImage Classificationimbalanced classificationDistribution Learning Based on Evolutionary Algorithm Assisted Deep Neural Networks for Imbalanced Image Classification
To address the trade-off problem of quality-diversity for the generated images in imbalanced classification tasks, we research on over-sampling based methods at the feature level instead of the data level and focus on se…
Diversityimage-classificationImage Classificationimbalanced classificationLabel-Imbalanced and Group-Sensitive Classification under Overparameterization
The goal in label-imbalanced and group-sensitive classification is to optimize relevant metrics such as balanced error and equal opportunity. Classical methods, such as weighted cross-entropy, fail when training deep net…
ClassificationGeneral Classification