Recent Advances in Zero-shot Recognition

TL;DR

This paper reviews recent progress in zero-shot recognition, a method enabling models to identify unseen categories without training data, discussing techniques, datasets, challenges, and future directions.

Contribution

It provides a comprehensive overview of zero-shot recognition methods, highlighting current limitations and suggesting future research directions in this emerging field.

Findings

Summarizes various zero-shot recognition techniques and their representations.

Discusses datasets and evaluation settings for zero-shot learning.

Identifies limitations and proposes future research directions.

Abstract

With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to scale the recognition to a large number of classes with few or now training samples for each class remains an unsolved problem. One approach to scaling up the recognition is to develop models capable of recognizing unseen categories without any training instances, or zero-shot recognition/ learning. This article provides a comprehensive review of existing zero-shot recognition techniques covering various aspects ranging from representations of models, and from datasets and evaluation settings. We also overview related recognition tasks including one-shot and open set recognition which can be used as natural extensions of zero-shot recognition when limited number of class samples become available or when zero-shot recognition is implemented in a real-world setting. Importantly, we highlight the limitations of existing approaches and point out future research directions in this existing new research area.