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

Tzuf Paz-Argaman, Reut Tsarfaty, Gal Chechik, Yuval Atzmon


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.
Anthology ID:
2020.findings-emnlp.50
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
569–579
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.50
DOI:
10.18653/v1/2020.findings-emnlp.50
Bibkey:
Cite (ACL):
Tzuf Paz-Argaman, Reut Tsarfaty, Gal Chechik, and Yuval Atzmon. 2020. ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 569–579, Online. Association for Computational Linguistics.
Cite (Informal):
ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization (Paz-Argaman et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.50.pdf
Code
 tzuf/ZEST
Data
CUB-200-2011