# Generating Multi-Center Classifier via Conditional Gaussian Distribution

arXiv: https://arxiv.org/abs/2401.15942 · HTML: https://mlsanity.com/paper/2401.15942/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 29 Jan 2024.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering](https://mlsanity.com/paper/1611.05148/) (2016)
- [SoftTriple Loss: Deep Metric Learning Without Triplet Sampling](https://mlsanity.com/paper/1909.05235/) (2019)
- [RepViT: Revisiting Mobile CNN From ViT Perspective](https://mlsanity.com/paper/2307.09283/) (2023)
- [Hyperbolic Vision Transformers: Combining Improvements in Metric Learning](https://mlsanity.com/paper/2203.10833/) (2022)
- [TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios](https://mlsanity.com/paper/2108.11539/) (2021)
- [Visual Recognition with Deep Nearest Centroids](https://mlsanity.com/paper/2209.07383/) (2022)
- [Learning Mixtures of Gaussians Using the DDPM Objective](https://mlsanity.com/paper/2307.01178/) (2023)
- [Improving Generalization via Scalable Neighborhood Component Analysis](https://mlsanity.com/paper/1808.04699/) (2018)
- [Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism](https://mlsanity.com/paper/2309.11331/) (2023)
- [Rethinking Feature Distribution for Loss Functions in Image Classification](https://mlsanity.com/paper/1803.02988/) (2018)
- [Non-isotropy Regularization for Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2203.08547/) (2022)
- [SG-Former: Self-guided Transformer with Evolving Token Reallocation](https://mlsanity.com/paper/2308.12216/) (2023)
- [A Softmax-free Loss Function Based on Predefined Optimal-distribution of Latent Features for Deep Learning Classifier](https://mlsanity.com/paper/2111.15449/) (2021)

## Abstract (arXiv)

The linear classifier is widely used in various image classification tasks. It works by optimizing the distance between a sample and its corresponding class center. However, in real-world data, one class can contain several local clusters, e.g., birds of different poses. To address this complexity, we propose a novel multi-center classifier. Different from the vanilla linear classifier, our proposal is established on the assumption that the deep features of the training set follow a Gaussian Mixture distribution. Specifically, we create a conditional Gaussian distribution for each class and then sample multiple sub-centers from that distribution to extend the linear classifier. This approach allows the model to capture intra-class local structures more efficiently. In addition, at test time we set the mean of the conditional Gaussian distribution as the class center of the linear classifier and follow the vanilla linear classifier outputs, thus requiring no additional parameters or computational overhead. Extensive experiments on image classification show that the proposed multi-center classifier is a powerful alternative to widely used linear classifiers. Code available at https://github.com/ZheminZhang1/MultiCenter-Classifier.