Enabling Generalized Zero-shot Learning Towards Unseen Domains by Intrinsic Learning from Redundant LLM Semantics

TL;DR

This paper introduces a novel approach called MDASR for cross-domain generalized zero-shot learning, which aligns redundant LLM-derived semantics with a shared feature space to improve recognition of unseen classes across domains.

Contribution

It proposes MDASR, a method that refines semantic representations by eliminating non-intrinsic semantics and simulating feature generation to enhance cross-domain GZSL performance.

Findings

MDASR improves recognition accuracy on Office-Home and Mini-DomainNet datasets.

Shared LLM-based semantics serve as a benchmark for future research.

Effective alignment reduces information asymmetry in cross-domain GZSL.

Abstract

Generalized zero-shot learning (GZSL) focuses on recognizing seen and unseen classes against domain shift problem where data of unseen classes may be misclassified as seen classes. However, existing GZSL is still limited to seen domains. In the current work, we study cross-domain GZSL (CDGZSL) which addresses GZSL towards unseen domains. Different from existing GZSL methods, CDGZSL constructs a common feature space across domains and acquires the corresponding intrinsic semantics shared among domains to transfer from seen to unseen domains. Considering the information asymmetry problem caused by redundant class semantics annotated with large language models (LLMs), we present Meta Domain Alignment Semantic Refinement (MDASR). Technically, MDASR consists of two parts: Inter-class similarity alignment, which eliminates the non-intrinsic semantics not shared across all domains under the guidance of inter-class feature relationships, and unseen-class meta generation, which preserves intrinsic semantics to maintain connectivity between seen and unseen classes by simulating feature generation. MDASR effectively aligns the redundant semantic space with the common feature space, mitigating the information asymmetry in CDGZSL. The effectiveness of MDASR is demonstrated on two datasets, Office-Home and Mini-DomainNet, and we have shared the LLM-based semantics for these datasets as a benchmark.