Zero-Shot Learning with Multi-Battery Factor Analysis

TL;DR

This paper introduces MBFA-ZSL, a novel approach that embeds multiple types of side information and visual features into a shared space for improved zero-shot learning, demonstrating superior results on standard datasets.

Contribution

It proposes a new Multi-Battery Factor Analysis method to unify different side information types into a single semantic space for zero-shot learning.

Findings

Outperforms state-of-the-art methods on AwA, CUB, and SUN datasets.

Efficient closed-form solution for large datasets.

Effectively leverages complementary side information types.

Abstract

Zero-shot learning (ZSL) extends the conventional image classification technique to a more challenging situation where the test image categories are not seen in the training samples. Most studies on ZSL utilize side information such as attributes or word vectors to bridge the relations between the seen classes and the unseen classes. However, existing approaches on ZSL typically exploit a shared space for each type of side information independently, which cannot make full use of the complementary knowledge of different types of side information. To this end, this paper presents an MBFA-ZSL approach to embed different types of side information as well as the visual feature into one shared space. Specifically, we first develop an algorithm named Multi-Battery Factor Analysis (MBFA) to build a unified semantic space, and then employ multiple types of side information in it to achieve the ZSL. The close-form solution makes MBFA-ZSL simple to implement and efficient to run on large datasets. Extensive experiments on the popular AwA, CUB, and SUN datasets show its significant superiority over the state-of-the-art approaches.