Deep Semi-supervised Metric Learning with Dual Alignment for Cervical Cancer Cell Detection

TL;DR

This paper introduces a deep semi-supervised metric learning approach with dual alignment for cervical cancer cell detection, effectively utilizing both labeled and unlabeled data to improve detection accuracy in medical imaging.

Contribution

It proposes a novel dual alignment strategy at proposal and prototype levels, along with a memory bank, to enhance semi-supervised learning in medical image detection.

Findings

Outperforms state-of-the-art semi-supervised methods

Effectively leverages unlabeled data for improved detection

Demonstrates robustness against noisy pseudo labels

Abstract

Deep learning has achieved unprecedented success in various object detection tasks with huge amounts of labeled data. However, obtaining large-scale annotations for medical images is extremely challenging due to the high demand of labour and expertise. In this paper, we propose a novel deep semi-supervised metric learning method to effectively leverage both labeled and unlabeled data for cervical cancer cell detection. Specifically, our model learns a metric space and conducts dual alignment of semantic features on both the proposal level and the prototype levels. On the proposal level, we align the unlabeled data with class proxies derived from the labeled data. We further align the prototypes of the labeled and unlabeled data to alleviate the influence of possibly noisy pseudo labels generated at the proposal alignment stage. Moreover, we adopt a memory bank to store the labeled prototypes, which significantly enrich the metric learning information from larger batches. Extensive experiments show our proposed method outperforms other state-of-the-art semi-supervised approaches consistently, demonstrating the efficacy of our proposed deep semi-supervised metric learning with dual alignment.