Transductive Multi-class and Multi-label Zero-shot Learning

TL;DR

This paper explores advanced zero-shot learning techniques, focusing on transductive methods and extending ZSL to handle multi-label scenarios, aiming to improve recognition of unseen classes.

Contribution

It introduces approaches that incorporate transductive learning and generalize ZSL to multi-label cases, enhancing the capability to recognize unseen classes more effectively.

Findings

Transductive ZSL improves recognition accuracy on unseen classes.

Multi-label ZSL extends applicability to more complex data.

Proposed methods outperform traditional ZSL approaches.

Abstract

Recently, zero-shot learning (ZSL) has received increasing interest. The key idea underpinning existing ZSL approaches is to exploit knowledge transfer via an intermediate-level semantic representation which is assumed to be shared between the auxiliary and target datasets, and is used to bridge between these domains for knowledge transfer. The semantic representation used in existing approaches varies from visual attributes to semantic word vectors and semantic relatedness. However, the overall pipeline is similar: a projection mapping low-level features to the semantic representation is learned from the auxiliary dataset by either classification or regression models and applied directly to map each instance into the same semantic representation space where a zero-shot classifier is used to recognise the unseen target class instances with a single known 'prototype' of each target class. In this paper we discuss two related lines of work improving the conventional approach: exploiting transductive learning ZSL, and generalising ZSL to the multi-label case.