Learning Robust Hash Codes for Multiple Instance Image Retrieval

TL;DR

This paper introduces a novel multiple instance deep hashing method for large-scale image retrieval, leveraging weak supervision and hierarchical representations to improve accuracy, especially in medical imaging contexts.

Contribution

It presents the first multiple instance deep hashing approach with a specialized pooling layer and robust training strategy, enhancing retrieval performance with weak bag-level supervision.

Findings

Outperforms state-of-the-art retrieval methods on mammography datasets

Effective in tumor assessment by modeling coexisting benign and malignant masses

Improves robustness and discriminability of hash codes in medical image retrieval

Abstract

In this paper, for the first time, we introduce a multiple instance (MI) deep hashing technique for learning discriminative hash codes with weak bag-level supervision suited for large-scale retrieval. We learn such hash codes by aggregating deeply learnt hierarchical representations across bag members through a dedicated MI pool layer. For better trainability and retrieval quality, we propose a two-pronged approach that includes robust optimization and training with an auxiliary single instance hashing arm which is down-regulated gradually. We pose retrieval for tumor assessment as an MI problem because tumors often coexist with benign masses and could exhibit complementary signatures when scanned from different anatomical views. Experimental validations on benchmark mammography and histology datasets demonstrate improved retrieval performance over the state-of-the-art methods.