Hierarchical Image Classification using Entailment Cone Embeddings
This work addresses the problem of enhancing image classification accuracy for researchers and practitioners by integrating label hierarchies, though it is incremental as it builds on existing CNN-based methods.
The paper tackled hierarchical image classification by leveraging semantic hierarchy information from class labels, showing that incorporating external semantic guidance alongside visual semantics improves performance, with empirical validation on the ETHEC dataset.
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.