.png){kind=icon}
返回
Generalized attention-based deep multi-instance learning
.png){kind=icon}
PRE
AI
DOI：10.1007/s00530-022-00992-w.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Attention-based deep multi-instance learning (MIL) is an effective and interpretable model. Its interpretability is attributed to the learnability of its inner attention-based MIL pooling. Its main problem is to learn a unique instance-level target concept for weighting instances. Another implicative issue is to assume that the bag and instance concepts are located in the same semantic space. In this paper, we relax these constraints as: (i) There exist multiple instance concepts; (ii) The bag and instance concepts live in different semantic spaces. Upon the two relaxed constraints, we propose a two-level attention-based MIL pooling that first learns several instance concepts in a low-level semantic space and subsequently captures the bag concept in a high-level semantic space. To effectively capture different types of instance concepts, we also present a new similarity-based loss. The experimental results show that our method achieves higher or very comparable performance with state-of-the-art methods on benchmark data sets and surpasses them in terms of performance and interpretability on a synthetic data set.
Keyword:
Multi-instance learning
Deep learning
Similarity-based loss
Attention-based pooling
Interpretability
期刊
IF:
3.1
论文数:
2.8K
被引数:
2.7K
机构
引用论文
Multi-instance clustering with applications to multi-instance prediction.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏分享收藏Landmark-based deep multi-instance learning for brain disease diagnosis基于Landmark的深度多示例学习在脑部疾病诊断中的应用MEDICAL IMAGE ANALYSIS
OAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAI分享收藏
查看更多内容