SALE: Self-adaptive LSH encoding for multi-instance learning

作者：

Highlights：

• A novel framework for multi-instance learning based on locality-sensitive hashing is proposed.

• A self-adaptive reconstruction improves the substitute’s representation of the bag.

• Key instances, correspondence relationship and co-occurrence information are used for learning.

• Experiments on different data sets demonstrate the general ability of high performance.

摘要

•A novel framework for multi-instance learning based on locality-sensitive hashing is proposed.•A self-adaptive reconstruction improves the substitute’s representation of the bag.•Key instances, correspondence relationship and co-occurrence information are used for learning.•Experiments on different data sets demonstrate the general ability of high performance.

论文关键词：Multi-instance learning,Machine learning,Locality-sensitive hashing,Self-adaptive learning

论文评审过程：Received 3 April 2016, Revised 10 April 2017, Accepted 29 April 2017, Available online 30 April 2017, Version of Record 12 July 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.04.029