.png){kind=icon}
返回
Incorporating attribute-level aligned comparative network for generalized zero-shot learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2023.127188.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The key challenge of zero -shot learning (ZSL) is to sufficiently disentangle each latent attribute from the class -level semantic annotations of images, thereby achieving a desirable semantic transfer to unseen classes with the disentangled attributes. However, most existing studies tackle the ZSL task with a strict classlevel alignment strategy that may yield insufficient disentanglement: (1) this strategy simply aligns holistic visual feature with its associated class -level semantic vector for each image; (2) the class -level semantic vectors have limited diversity and complex compositions of attributes. To address these issues, we propose an incorporating attribute -level aligned comparative network, i.e., IAAC-net, that develops the alignment strategy of ZSL to the attribute level. IAAC-net aims to establish diversified attribute -level and refined class -level alignments to facilitate attribute disentanglement and simultaneously improve zero -shot generalization. By further proposing a confusion -aware loss, the model is forced to rectify the disentanglement of indistinguishable attributes, which leads to a more accurate attribute disentanglement. The proposed IAAC-net yields significant improvements over the strong baselines, leading to new state-of-the-art performances on three popular challenging benchmarks, i.e., CUB, SUN, and AWA2.
Keyword:
Zero-shot learning
Visual-semantic alignment
Representation learning
Transfer learning
Image classification
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
.png){kind=icon}
分享收藏A Novel Perspective to Zero-Shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion零射击学习的新视角: 通过语义特征扩展实现流形结构的对齐
OAAI
OAAI分享收藏分享收藏
查看更多内容