# Max-margin Class Imbalanced Learning with Gaussian Affinity

arXiv: https://arxiv.org/abs/1901.07711 · HTML: https://mlsanity.com/paper/1901.07711/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2019.

## Built on by (most cited first, 7 of 7)

- [ShaSTA: Modeling Shape and Spatio-Temporal Affinities for 3D Multi-Object Tracking](https://mlsanity.com/paper/2211.03919/) (2022)
- [On-target Adaptation](https://mlsanity.com/paper/2109.01087/) (2021)
- [A Closer Look at Prototype Classifier for Few-shot Image Classification](https://mlsanity.com/paper/2110.05076/) (2021)
- [MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classes](https://mlsanity.com/paper/2404.09232/) (2024)
- [Incremental Cross-Domain Adaptation for Robust Retinopathy Screening via Bayesian Deep Learning](https://mlsanity.com/paper/2110.09319/) (2021)
- [Self-Paced Imbalance Rectification for Class Incremental Learning](https://mlsanity.com/paper/2202.03703/) (2022)
- [Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods](https://mlsanity.com/paper/2202.09964/) (2022)

## Abstract (arXiv)

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.