Hierarchical Image Classification Using Entailment Cone Embeddings

Abstract

Image classification has been studied extensively, but there has been limited work in using unconventional, external guidance other than traditional image-label pairs for training. We present a set of methods for leveraging information about the semantic hierarchy embedded in class labels. We first inject label-hierarchy knowledge into an arbitrary CNN-based classifier and empirically show that availability of such external semantic information in conjunction with the visual semantics from images boosts overall performance. Taking a step further in this direction, we model more explicitly the label-label and label-image interactions using order-preserving embeddings governed by both Euclidean and hyperbolic geometries, prevalent in natural language, and tailor them to hierarchical image classification and representation learning. We empirically validate all the models on the hierarchical ETHEC dataset.

Cite

Text

Dhall et al. "Hierarchical Image Classification Using Entailment Cone Embeddings." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00426

Markdown

[Dhall et al. "Hierarchical Image Classification Using Entailment Cone Embeddings." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/dhall2020cvprw-hierarchical/) doi:10.1109/CVPRW50498.2020.00426

BibTeX

@inproceedings{dhall2020cvprw-hierarchical,
  title     = {{Hierarchical Image Classification Using Entailment Cone Embeddings}},
  author    = {Dhall, Ankit and Makarova, Anastasia and Ganea, Octavian and Pavllo, Dario and Greeff, Michael and Krause, Andreas},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2020},
  pages     = {3649-3658},
  doi       = {10.1109/CVPRW50498.2020.00426},
  url       = {https://mlanthology.org/cvprw/2020/dhall2020cvprw-hierarchical/}
}