Multiple Instance Learning with Differential Evolutionary Pooling

Multiple Instance Learning with Differential Evolutionary Pooling

While implementing Multiple Instance Learning (MIL) through Deep Neural Networks, the most important task is to design the bag-level pooling function that defines the instance-to-bag relationship and eventually determines the class label of a bag. In this article, Differential Evolutionary (DE) pool...

Full description

Bibliographic Details
Main Authors: Kamanasish Bhattacharjee, Arti Tiwari, Millie Pant, Chang Wook Ahn, Sanghoun Oh
Format: Article
Language:English
Published: MDPI AG 2021-06-01
Series:Electronics
Subjects:
Multiple Instance Learning (MIL)
Differential Evolution (DE)
pooling
adaptive
variant
parameter
Online Access:https://www.mdpi.com/2079-9292/10/12/1403

Internet

https://www.mdpi.com/2079-9292/10/12/1403

Similar Items