# AMS-SFE: Towards an Alignment of Manifold Structures via Semantic Feature Expansion for Zero-shot Learning

## TL;DR

This paper introduces AMS-SFE, a novel zero-shot learning model that expands semantic features and aligns manifold structures to improve recognition of unseen classes, effectively addressing domain shift issues.

## Contribution

The paper proposes a new autoencoder-based approach to expand semantic features and align them with visual feature manifolds, pioneering this alignment method in zero-shot learning.

## Key findings

- Significant performance improvements over existing ZSL methods.
- Effective semantic feature expansion via autoencoder.
- Successful alignment of semantic and visual feature manifolds.

## Abstract

Zero-shot learning (ZSL) aims at recognizing unseen classes with knowledge transferred from seen classes. This is typically achieved by exploiting a semantic feature space (FS) shared by both seen and unseen classes, i.e., attributes or word vectors, as the bridge. However, due to the mutually disjoint of training (seen) and testing (unseen) data, existing ZSL methods easily and commonly suffer from the domain shift problem. To address this issue, we propose a novel model called AMS-SFE. It considers the Alignment of Manifold Structures by Semantic Feature Expansion. Specifically, we build up an autoencoder based model to expand the semantic features and joint with an alignment to an embedded manifold extracted from the visual FS of data. It is the first attempt to align these two FSs by way of expanding semantic features. Extensive experiments show the remarkable performance improvement of our model compared with other existing methods.