Deconstructed Generation-Based Zero-Shot Model
Chen, Dubing, Shen, Yuming, Zhang, Haofeng, Torr, Philip H. S.
–arXiv.org Artificial Intelligence
Recent research on Generalized Zero-Shot Learning (GZSL) has focused primarily on generation-based methods. However, current literature has overlooked the fundamental principles of these methods and has made limited progress in a complex manner. In this paper, we aim to deconstruct the generator-classifier framework and provide guidance for its improvement and extension. We begin by breaking down the generator-learned unseen class distribution into class-level and instance-level distributions. Through our analysis of the role of these two types of distributions in solving the GZSL problem, we generalize the focus of the generation-based approach, emphasizing the importance of (i) attribute generalization in generator learning and (ii) independent classifier learning with partially biased data. We present a simple method based on this analysis that outperforms SotAs on four public GZSL datasets, demonstrating the validity of our deconstruction. Furthermore, our proposed method remains effective even without a generative model, representing a step towards simplifying the generator-classifier structure. Our code is available at \url{https://github.com/cdb342/DGZ}.
arXiv.org Artificial Intelligence
Mar-7-2023
- Country:
- Asia (0.28)
- Genre:
- Research Report > New Finding (0.66)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Natural Language > Large Language Model (0.64)
- Representation & Reasoning (1.00)
- Vision (0.94)
- Information Technology > Artificial Intelligence