ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization

TL;DR

This paper introduces ZEST, a zero-shot learning approach that leverages textual similarity and visual summaries from descriptions to improve recognition of unseen bird species in images, significantly outperforming existing methods.

Contribution

The paper presents a novel attention-based model that incorporates textual similarity and visual summaries, enhancing zero-shot image recognition from text descriptions.

Findings

Significant performance improvements over state-of-the-art methods.

Effective use of textual similarity for knowledge transfer.

Visual summaries improve the focus on relevant features.

Abstract

We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to classify images of previously-unseen species based on specie descriptions. This setup has been studied in the vision community under the name zero-shot learning from text, focusing on learning to transfer knowledge about visual aspects of birds from seen classes to previously-unseen ones. Here, we suggest focusing on the textual description and distilling from the description the most relevant information to effectively match visual features to the parts of the text that discuss them. Specifically, (1) we propose to leverage the similarity between species, reflected in the similarity between text descriptions of the species. (2) we derive visual summaries of the texts, i.e., extractive summaries that focus on the visual features that tend to be reflected in images. We propose a simple attention-based model augmented with the similarity and visual summaries components. Our empirical results consistently and significantly outperform the state-of-the-art on the largest benchmarks for text-based zero-shot learning, illustrating the critical importance of texts for zero-shot image-recognition.