# Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers

arXiv: https://arxiv.org/abs/2112.02353 · HTML: https://mlsanity.com/paper/2112.02353/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 68 references that are in the map.
- First posted on arXiv 4 Dec 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Few-Shot Image Recognition by Predicting Parameters from Activations](https://mlsanity.com/paper/1706.03466/) (2017)
- [Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks](https://mlsanity.com/paper/1912.09393/) (2019)
- [Towards better decoding and language model integration in sequence to sequence models](https://mlsanity.com/paper/1612.02695/) (2016)
- [Coherent Hierarchical Multi-Label Classification Networks](https://mlsanity.com/paper/2010.10151/) (2020)
- [Do Convolutional Neural Networks Learn Class Hierarchy?](https://mlsanity.com/paper/1710.06501/) (2017)
- [Hierarchical Image Classification using Entailment Cone Embeddings](https://mlsanity.com/paper/2004.03459/) (2020)
- [Low-shot learning with large-scale diffusion](https://mlsanity.com/paper/1706.02332/) (2017)
- [Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding](https://mlsanity.com/paper/1808.04505/) (2018)
- [Label Confusion Learning to Enhance Text Classification Models](https://mlsanity.com/paper/2012.04987/) (2020)
- [Hierarchical Classification of Pulmonary Lesions: A Large-Scale Radio-Pathomics Study](https://mlsanity.com/paper/2010.04049/) (2020)

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

- [Class Similarity Transition: Decoupling Class Similarities and Imbalance from Generalized Few-shot Segmentation](https://mlsanity.com/paper/2404.05111/) (2024)
- [Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions](https://mlsanity.com/paper/2505.23031/) (2025)
- [An Analysis of Multi-Task Architectures for the Hierarchic Multi-Label Problem of Vehicle Model and Make Classification](https://mlsanity.com/paper/2603.01746/) (2026)

## Abstract (arXiv)

Hierarchical classification aims to sort the object into a hierarchical structure of categories. For example, a bird can be categorized according to a three-level hierarchy of order, family, and species. Existing methods commonly address hierarchical classification by decoupling it into a series of multi-class classification tasks. However, such a multi-task learning strategy fails to fully exploit the correlation among various categories across different levels of the hierarchy. In this paper, we propose Label Hierarchy Transition (LHT), a unified probabilistic framework based on deep learning, to address the challenges of hierarchical classification. The LHT framework consists of a transition network and a confusion loss. The transition network focuses on explicitly learning the label hierarchy transition matrices, which has the potential to effectively encode the underlying correlations embedded within class hierarchies. The confusion loss encourages the classification network to learn correlations across different label hierarchies during training. The proposed framework can be readily adapted to any existing deep network with only minor modifications. We experiment with a series of public benchmark datasets for hierarchical classification problems, and the results demonstrate the superiority of our approach beyond current state-of-the-art methods. Furthermore, we extend our proposed LHT framework to the skin lesion diagnosis task and validate its great potential in computer-aided diagnosis. The code of our method is available at hrefhttps://github.com/renzhenwang/label-hierarchy-transitionhttps://github.com/renzhenwang/label-hierarchy-transition.