# CrowdAttention: An Attention Based Framework to Classify Crowdsourced Data in Medical Scenarios

## TL;DR

The paper introduces CrowdAttention, a deep learning framework that improves classification accuracy by modeling annotator reliability in crowdsourced medical data.

## Contribution

CrowdAttention introduces a novel cross-attention mechanism to jointly model classification and annotator reliability in crowdsourced data.

## Key findings

- CrowdAttention outperforms state-of-the-art methods in accuracy and robustness on synthetic and real-world datasets.
- The framework effectively handles label noise by assigning reliability scores based on annotator alignment with model predictions.

## Abstract

Supervised learning models in healthcare and other domains heavily depend on high-quality, labeled data. However, acquiring expert-verified labels (i.e., the gold standard) is often impractical due to cost, time, and subjectivity. Crowdsourcing offers a scalable alternative by collecting labels from multiple non-expert annotators; however, it introduces label noise due to the heterogeneity of annotators. In this work, we propose CrowdAttention, a novel end-to-end deep learning framework that jointly models classification and annotator reliability using a cross-attention mechanism. The architecture consists of two coupled networks: a classification network that estimates the latent true label, and a crowd network that assigns instance-dependent reliability scores to each annotator’s label based on its alignment with the model’s current prediction. We demonstrate the effectiveness of our approach on both synthetic and real-world datasets, showing improved accuracy and robustness compared to state-of-the-art multi-annotator learning methods.