# B-CNN: Branch Convolutional Neural Network for Hierarchical Classification

arXiv: https://arxiv.org/abs/1709.09890 · HTML: https://mlsanity.com/paper/1709.09890/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2017.

## Built on by (most cited first, 30 of 37)

- [Deep Hierarchical Semantic Segmentation](https://mlsanity.com/paper/2203.14335/) (2022)
- [Crop mapping from image time series: deep learning with multi-scale label hierarchies](https://mlsanity.com/paper/2102.08820/) (2021)
- [Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer](https://mlsanity.com/paper/2101.09536/) (2021)
- [Skin Lesion Recognition with Class-Hierarchy Regularized Hyperbolic Embeddings](https://mlsanity.com/paper/2209.05842/) (2022)
- [Visually Consistent Hierarchical Image Classification](https://mlsanity.com/paper/2406.11608/) (2024)
- [Hierarchical classification at multiple operating points](https://mlsanity.com/paper/2210.10929/) (2022)
- [ProTeCt: Prompt Tuning for Taxonomic Open Set Classification](https://mlsanity.com/paper/2306.02240/) (2023)
- [Semi-Supervised Learning with Taxonomic Labels](https://mlsanity.com/paper/2111.11595/) (2021)
- [A Systematic Literature Review of Automated ICD Coding and Classification Systems using Discharge Summaries](https://mlsanity.com/paper/2107.10652/) (2021)
- [E-PixelHop: An Enhanced PixelHop Method for Object Classification](https://mlsanity.com/paper/2107.02966/) (2021)
- [Dynamic ConvNets on Tiny Devices via Nested Sparsity](https://mlsanity.com/paper/2203.03324/) (2022)
- [Video-based Hierarchical Species Classification for Longline Fishing Monitoring](https://mlsanity.com/paper/2102.03520/) (2021)
- [Prototype Based Classification from Hierarchy to Fairness](https://mlsanity.com/paper/2205.13997/) (2022)
- [A Capsule Network for Hierarchical Multi-Label Image Classification](https://mlsanity.com/paper/2209.05723/) (2022)
- [Coping with Change: Learning Invariant and Minimum Sufficient Representations for Fine-Grained Visual Categorization](https://mlsanity.com/paper/2306.04893/) (2023)
- [United We Learn Better: Harvesting Learning Improvements From Class Hierarchies Across Tasks](https://mlsanity.com/paper/2107.13627/) (2021)
- [Encoding Hierarchical Information in Neural Networks helps in Subpopulation Shift](https://mlsanity.com/paper/2112.10844/) (2021)
- [Towards Understanding the Effect of Pretraining Label Granularity](https://mlsanity.com/paper/2303.16887/) (2023)
- [Taxonomic Class Incremental Learning](https://mlsanity.com/paper/2304.05547/) (2023)
- [Improving the Reproducibility of Deep Learning Software: An Initial Investigation through a Case Study Analysis](https://mlsanity.com/paper/2505.03165/) (2025)
- [Hierarchical knowledge guided fault intensity diagnosis of complex industrial systems](https://mlsanity.com/paper/2508.12375/) (2025)
- [Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expression](https://mlsanity.com/paper/2206.11049/) (2022)
- [Concept Drift and Long-Tailed Distribution in Fine-Grained Visual Categorization: Benchmark and Method](https://mlsanity.com/paper/2306.02346/) (2023)
- [Informed deep hierarchical classification: a non-standard analysis inspired approach](https://mlsanity.com/paper/2409.16956/) (2024)
- [SoilNet: A Multimodal Multitask Model for Hierarchical Classification of Soil Horizons](https://mlsanity.com/paper/2508.03785/) (2025)
- [Dysplasia grading of colorectal polyps through CNN analysis of WSI](https://mlsanity.com/paper/2102.05498/) (2021)
- [HCIL: Hierarchical Class Incremental Learning for Longline Fishing Visual Monitoring](https://mlsanity.com/paper/2202.13018/) (2022)
- [Deep Learning with Label Noise: A Hierarchical Approach](https://mlsanity.com/paper/2205.14299/) (2022)
- [Light-weight CNN-based VVC Inter Partitioning Acceleration](https://mlsanity.com/paper/2312.10567/) (2023)
- [A class-driven hierarchical ResNet for classification of multispectral remote sensing images](https://mlsanity.com/paper/2510.08060/) (2025)

## Abstract (arXiv)

Convolutional Neural Network (CNN) image classifiers are traditionally designed to have sequential convolutional layers with a single output layer. This is based on the assumption that all target classes should be treated equally and exclusively. However, some classes can be more difficult to distinguish than others, and classes may be organized in a hierarchy of categories. At the same time, a CNN is designed to learn internal representations that abstract from the input data based on its hierarchical layered structure. So it is natural to ask if an inverse of this idea can be applied to learn a model that can predict over a classification hierarchy using multiple output layers in decreasing order of class abstraction. In this paper, we introduce a variant of the traditional CNN model named the Branch Convolutional Neural Network (B-CNN). A B-CNN model outputs multiple predictions ordered from coarse to fine along the concatenated convolutional layers corresponding to the hierarchical structure of the target classes, which can be regarded as a form of prior knowledge on the output. To learn with B-CNNs a novel training strategy, named the Branch Training strategy (BT-strategy), is introduced which balances the strictness of the prior with the freedom to adjust parameters on the output layers to minimize the loss. In this way we show that CNN based models can be forced to learn successively coarse to fine concepts in the internal layers at the output stage, and that hierarchical prior knowledge can be adopted to boost CNN models' classification performance. Our models are evaluated to show that the B-CNN extensions improve over the corresponding baseline CNN on the benchmark datasets MNIST, CIFAR-10 and CIFAR-100.