Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning
원문 초록
Zero-shot learning (ZSL) has been shown to be a promising approach to generalizing a model to categories unseen during training by leveraging class attributes, but challenges still remain. Recently, methods using generative models to combat bias towards classes seen during training have pushed the state of the art of ZSL, but these generative models can be slow or computationally expensive to train. Additionally, while many previous ZSL methods assume a one-time adaptation to unseen classes, in reality, the world is always changing, necessitating a constant adjustment for deployed models. Models unprepared to handle a sequential stream of data are likely to experience catastrophic forgetting. We propose a meta-continual zero-shot learning (MCZSL) approach to address both these issues. In particular, by pairing self-gating of attributes and scaled class normalization with meta-learning based training, we are able to outperform state-of-the-art results while being able to train our models substantially faster ($>100\times$) than expensive generative-based approaches. We demonstrate this by performing experiments on five standard ZSL datasets (CUB, aPY, AWA1, AWA2 and SUN) in both generalized zero-shot learning and generalized continual zero-shot learning settings.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Zero-Shot Learning Based Approach For Medieval Word Recognition Using Deep-Learned Features
A Brain Graph Foundation Model: Pre-Training and Prompt-Tuning for Any Atlas and Disorder
Hyperbolic Dual Feature Augmentation for Open-Environment
Feasibility with Language Models for Open-World Compositional Zero-Shot Learning
Multiple-Input Multiple-Output Fusion Network For Generalized Zero-Shot Learning
Attribute-Based Classification for Zero-Shot Visual Object Categorization
토론
이 논문과 연결된 포럼 글이 아직 없습니다.