MetaZero: A Novel Meta-Learning Method Suitable for Generalized Zero-Shot Learning
Year: 2025
Type: article
Abstract: Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and unseen classes, when only the labeled examples from seen classes are provided. Most GZSL methods only optimize models based on seen classes but fail to explicitly mimic zero-shot learning settings that transfer knowledge from seen classes to unseen classes at the training time. Meta-learning has been introduced to mitigate this problem, but the models of current meta-learning approaches only learn to face the novel classes rather than learn to face the strong biased problem during the training, which is the main reason for the poor performance of most methods in GZSL. Humans can improve their knowledge with well-designed tests. According to this phenomenon, We propose a novel meta-learning method that is more suitable for GZSL termed MetaZero, aiming to alleviate the strong bias problem in GZSL. Specifically, MetaZero modifies the division of meta train set and meta test set, so that the model can directly face the strong bias problem in the meta test stage. In this way, with the iteration of training, the model can become an expert to solve the strong bias problem. Our extensive experiments manifest that our method achieves the significant gains than the SOTA GZSL methods.
Source: IEEE Access
Authors: Zeqing Zhang, Zefei Zhang, Na Jin, Fanchang Yang, Wei Zhao
Institution: West Yunnan University of Applied Sciences
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,075
OpenAlex ID: W4409249384