返回
Multi-attention multiple instance learning
DOI:10.1007/s00521-022-07259-5.png)
摘要
En 中文
A new multi-attention based method for solving the MIL problem (MAMIL), which takes into account the neighboring patches or instances of each analyzed patch in a bag, is proposed. In the method, one of the attention modules takes into account adjacent patches or instances, several attention modules are used to get a diverse feature representation of patches, and one attention module is used to unite different feature representations to provide an accurate classification of each patch (instance) and the whole bag. Due to MAMIL, a combined representation of patches and their neighbors in the form of embeddings of a small dimensionality for simple classification is realized. Moreover, different types of patches are efficiently processed, and a diverse feature representation of patches in a bag by using several attention modules is implemented. A simple approach for explaining the classification predictions of patches is proposed. Numerical experiments with various datasets illustrate the proposed method.
Keyword:
Multiple instance learning
Attention mechanism
Classification
Explanation
期刊
IF:
4.5
论文数:
2.4K
被引数:
3.4W
机构
引用论文
Interpretable machine learning: Fundamental principles and 10 grand challenges可解释的机器学习: 基本原则和十大挑战
STATISTICS SURVEYS
IF15.4

