# MSE Loss with Outlying Label for Imbalanced Classification

arXiv: https://arxiv.org/abs/2107.02393 · HTML: https://mlsanity.com/paper/2107.02393/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 6 Jul 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [Rethinking the Value of Labels for Improving Class-Imbalanced Learning](https://mlsanity.com/paper/2006.07529/) (2020)
- [Gradient Harmonized Single-stage Detector](https://mlsanity.com/paper/1811.05181/) (2018)
- [YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video](https://mlsanity.com/paper/1702.00824/) (2017)
- [Data Augmentation using Random Image Cropping and Patching for Deep CNNs](https://mlsanity.com/paper/1811.09030/) (2018)
- [FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation](https://mlsanity.com/paper/1903.11816/) (2019)
- [Improved Mixed-Example Data Augmentation](https://mlsanity.com/paper/1805.11272/) (2018)
- [Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance](https://mlsanity.com/paper/2010.01824/) (2020)

## Built on by (most cited first, 3 of 3)

- [Traffic incident duration prediction via a deep learning framework for text description encoding](https://mlsanity.com/paper/2209.08735/) (2022)
- [Use of triplet loss for facial restoration in low-resolution images](https://mlsanity.com/paper/2409.03530/) (2024)
- [Deep Learning for Micro-Scale Crack Detection on Imbalanced Datasets Using Key Point Localization](https://mlsanity.com/paper/2411.10389/) (2024)

## Abstract (arXiv)

In this paper, we propose mean squared error (MSE) loss with outlying label for class imbalanced classification. Cross entropy (CE) loss, which is widely used for image recognition, is learned so that the probability value of true class is closer to one by back propagation. However, for imbalanced datasets, the learning is insufficient for the classes with a small number of samples. Therefore, we propose a novel classification method using the MSE loss that can be learned the relationships of all classes no matter which image is input. Unlike CE loss, MSE loss is possible to equalize the number of back propagation for all classes and to learn the feature space considering the relationships between classes as metric learning. Furthermore, instead of the usual one-hot teacher label, we use a novel teacher label that takes the number of class samples into account. This induces the outlying label which depends on the number of samples in each class, and the class with a small number of samples has outlying margin in a feature space. It is possible to create the feature space for separating high-difficulty classes and low-difficulty classes. By the experiments on imbalanced classification and semantic segmentation, we confirmed that the proposed method was much improved in comparison with standard CE loss and conventional methods, even though only the loss and teacher labels were changed.