Nested multi-instance image classification

Alexander Stec, Diego Klabjan, Jean Utke

Research output: Contribution to journalArticlepeer-review

Abstract

There are classification tasks that take as inputs groups of images rather than single images. In order to address such situations, we introduce a nested multi-instance deep network. The approach is generic in that it is applicable to general data instances, not just images. The network has several convolutional neural networks grouped together at different stages. This primarily differs from other previous works in that we organize instances into relevant groups that are treated differently. We also introduce a method to replace instances that are missing which successfully creates neutral input instances and consistently outperforms standard fill-in methods in real world use cases. In addition, we propose a method for manual dropout when a whole group of instances is missing that allows us to use richer training data and obtain higher accuracy at the end of training. With specific pretraining, we find that the model works to great effect on our real world and public datasets in comparison to baseline methods, with our improvements ranging from 1% to 5%.

Original languageEnglish (US)
JournalUnknown Journal
StatePublished - Aug 30 2018

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'Nested multi-instance image classification'. Together they form a unique fingerprint.

Cite this