# Harnessing Superclasses for Learning from Hierarchical Databases

arXiv: https://arxiv.org/abs/2411.16438 · HTML: https://mlsanity.com/paper/2411.16438/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 36 references that are in the map.
- First posted on arXiv 25 Nov 2024.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets](https://mlsanity.com/paper/1707.08819/) (2017)
- [Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks](https://mlsanity.com/paper/1912.09393/) (2019)
- [Tree-Sliced Variants of Wasserstein Distances](https://mlsanity.com/paper/1902.00342/) (2019)
- [Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier](https://mlsanity.com/paper/2007.09898/) (2020)
- [Learning Hierarchy Aware Features for Reducing Mistake Severity](https://mlsanity.com/paper/2207.12646/) (2022)
- [No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks](https://mlsanity.com/paper/2104.00795/) (2021)
- [A hierarchical loss and its problems when classifying non-hierarchically](https://mlsanity.com/paper/1709.01062/) (2017)
- [Combined convolutional and recurrent neural networks for hierarchical classification of images](https://mlsanity.com/paper/1809.09574/) (2018)
- [HiNet: Hierarchical Classification with Neural Network](https://mlsanity.com/paper/1705.11105/) (2017)

## Built on by (most cited first, 1 of 1)

- [Hier-COS: Making Deep Features Hierarchy-aware via Composition of Orthogonal Subspaces](https://mlsanity.com/paper/2503.07853/) (2025)

## Abstract (arXiv)

In many large-scale classification problems, classes are organized in a known hierarchy, typically represented as a tree expressing the inclusion of classes in superclasses. We introduce a loss for this type of supervised hierarchical classification. It utilizes the knowledge of the hierarchy to assign each example not only to a class but also to all encompassing superclasses. Applicable to any feedforward architecture with a softmax output layer, this loss is a proper scoring rule, in that its expectation is minimized by the true posterior class probabilities. This property allows us to simultaneously pursue consistent classification objectives between superclasses and fine-grained classes, and eliminates the need for a performance trade-off between different granularities. We conduct an experimental study on three reference benchmarks, in which we vary the size of the training sets to cover a diverse set of learning scenarios. Our approach does not entail any significant additional computational cost compared with the loss of cross-entropy. It improves accuracy and reduces the number of coarse errors, with predicted labels that are distant from ground-truth labels in the tree.