.png){kind=icon}
返回
Contrastive Prototype-Guided Generation for Generalized Zero-Shot Learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2024.106324.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Generalized zero -shot learning (GZSL) aims to recognize both seen and unseen classes, while only samples from seen classes are available for training. The mainstream methods mitigate the lack of unseen training data by simulating the visual unseen samples. However, the sample generator is actually learned with just seen -class samples, and semantic descriptions of unseen classes are just provided to the pre -trained sample generator for unseen data generation, therefore, the generator would have bias towards seen categories, and the unseen generation quality, including both precision and diversity, is still the main learning challenge. To this end, we propose a Prototype -Guided Generation for Generalized Zero -Shot Learning (PGZSL), in order to guide the sample generation with unseen knowledge. First, unseen data generation is guided and rectified in PGZSL by contrastive prototypical anchors with both class semantic consistency and feature discriminability. Second, PGZSL introduces Certainty -Driven Mixup for generator to enrich the diversity of generated unseen samples, while suppress the generation of uncertain boundary samples as well. Empirical results over five benchmark datasets show that PGZSL significantly outperforms the SOTA methods in both ZSL and GZSL tasks.
Keyword:
Zero-shot learning
Generative adversarial network
Contrastive prototype
Feature diversity
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
暂无机构信息
引用论文
.png){kind=icon}
分享收藏
查看更多内容