# Learning Visually Consistent Label Embeddings for Zero-Shot Learning

arXiv: https://arxiv.org/abs/1905.06764 · HTML: https://mlsanity.com/paper/1905.06764/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2019.

## Built on by (most cited first, 1 of 1)

- [Zero-Shot Aerial Object Detection with Visual Description Regularization](https://mlsanity.com/paper/2402.18233/) (2024)

## Abstract (arXiv)

In this work, we propose a zero-shot learning method to effectively model knowledge transfer between classes via jointly learning visually consistent word vectors and label embedding model in an end-to-end manner. The main idea is to project the vector space word vectors of attributes and classes into the visual space such that word representations of semantically related classes become more closer, and use the projected vectors in the proposed embedding model to identify unseen classes. We evaluate the proposed approach on two benchmark datasets and the experimental results show that our method yields significant improvements in recognition accuracy.