# Hierarchical Image Classification with A Literally Toy Dataset

arXiv: https://arxiv.org/abs/2111.00892 · HTML: https://mlsanity.com/paper/2111.00892/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 38 references that are in the map.
- First posted on arXiv 1 Nov 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection](https://mlsanity.com/paper/1607.07155/) (2016)
- [Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks](https://mlsanity.com/paper/1512.04143/) (2015)
- [HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection](https://mlsanity.com/paper/1604.00600/) (2016)
- [Vehicle Re-identification with Viewpoint-aware Metric Learning](https://mlsanity.com/paper/1910.04104/) (2019)
- [Person Re-identification with Metric Learning using Privileged Information](https://mlsanity.com/paper/1904.05005/) (2019)
- [Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales](https://mlsanity.com/paper/2103.11781/) (2021)

## Built on by (most cited first, 2 of 2)

- [Muti-Stage Hierarchical Food Classification](https://mlsanity.com/paper/2309.01075/) (2023)
- [Enhancing Classification with Hierarchical Scalable Query on Fusion Transformer](https://mlsanity.com/paper/2302.14487/) (2023)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) in image classification remains a big challenge. In existing UDA image dataset, classes are usually organized in a flattened way, where a plain classifier can be trained. Yet in some scenarios, the flat categories originate from some base classes. For example, buggies belong to the class bird. We define the classification task where classes have characteristics above and the flat classes and the base classes are organized hierarchically as hierarchical image classification. Intuitively, leveraging such hierarchical structure will benefit hierarchical image classification, e.g., two easily confusing classes may belong to entirely different base classes. In this paper, we improve the performance of classification by fusing features learned from a hierarchy of labels. Specifically, we train feature extractors supervised by hierarchical labels and with UDA technology, which will output multiple features for an input image. The features are subsequently concatenated to predict the finest-grained class. This study is conducted with a new dataset named Lego-15. Consisting of synthetic images and real images of the Lego bricks, the Lego-15 dataset contains 15 classes of bricks. Each class originates from a coarse-level label and a middle-level label. For example, class "85080" is associated with bricks (coarse) and bricks round (middle). In this dataset, we demonstrate that our method brings about consistent improvement over the baseline in UDA in hierarchical image classification. Extensive ablation and variant studies provide insights into the new dataset and the investigated algorithm.