Evolutionary Generalized Zero-Shot Learning
arxiv(2022)
摘要
Attribute-based Zero-Shot Learning (ZSL) has revolutionized the ability of
models to recognize new classes not seen during training. However, with the
advancement of large-scale models, the expectations have risen. Beyond merely
achieving zero-shot generalization, there is a growing demand for universal
models that can continually evolve in expert domains using unlabeled data. To
address this, we introduce a scaled-down instantiation of this challenge:
Evolutionary Generalized Zero-Shot Learning (EGZSL). This setting allows a
low-performing zero-shot model to adapt to the test data stream and evolve
online. We elaborate on three challenges of this special task, ,
catastrophic forgetting, initial prediction bias, and evolutionary data class
bias. Moreover, we propose targeted solutions for each challenge, resulting in
a generic method capable of continuous evolution from a given initial IGZSL
model. Experiments on three popular GZSL benchmark datasets demonstrate that
our model can learn from the test data stream while other baselines fail. Codes
are available at .
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要