Saved in:
Bibliographic Details
Main Authors: Yue, Jiaqi, Zhao, Chunhui, Zhao, Jiancheng, Huang, Biao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.14362
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912265994764288
author Yue, Jiaqi
Zhao, Chunhui
Zhao, Jiancheng
Huang, Biao
author_facet Yue, Jiaqi
Zhao, Chunhui
Zhao, Jiancheng
Huang, Biao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14362
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enabling Generalized Zero-shot Learning Towards Unseen Domains by Intrinsic Learning from Redundant LLM Semantics
Yue, Jiaqi
Zhao, Chunhui
Zhao, Jiancheng
Huang, Biao
Computer Vision and Pattern Recognition
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.
title Enabling Generalized Zero-shot Learning Towards Unseen Domains by Intrinsic Learning from Redundant LLM Semantics
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.14362