# Zero-Shot Learning by Generating Pseudo Feature Representations

## TL;DR

This paper introduces a novel zero-shot learning method that generates pseudo feature representations for unseen classes, improving recognition accuracy by synthesizing features based on attribute information.

## Contribution

The paper proposes a simple yet effective approach using pseudo feature generation and a joint attribute extractor, advancing zero-shot learning performance on multiple datasets.

## Key findings

- Significant improvement in zero-shot recognition accuracy.
- Enhanced zero-shot retrieval performance with higher mAP.
- Effective synthesis of features for unseen classes.

## Abstract

Zero-shot learning (ZSL) is a challenging task aiming at recognizing novel classes without any training instances. In this paper we present a simple but high-performance ZSL approach by generating pseudo feature representations (GPFR). Given the dataset of seen classes and side information of unseen classes (e.g. attributes), we synthesize feature-level pseudo representations for novel concepts, which allows us access to the formulation of unseen class predictor. Firstly we design a Joint Attribute Feature Extractor (JAFE) to acquire understandings about attributes, then construct a cognitive repository of attributes filtered by confidence margins, and finally generate pseudo feature representations using a probability based sampling strategy to facilitate subsequent training process of class predictor. We demonstrate the effectiveness in ZSL settings and the extensibility in supervised recognition scenario of our method on a synthetic colored MNIST dataset (C-MNIST). For several popular ZSL benchmark datasets, our approach also shows compelling results on zero-shot recognition task, especially leading to tremendous improvement to state-of-the-art mAP on zero-shot retrieval task.