# Cross-Feature Hybrid Associative Priori Network for Pulsar Candidate Screening

## TL;DR

This paper introduces a new neural network, CFHAPNet, that improves pulsar signal recognition by combining multi-channel data processing and attention mechanisms.

## Contribution

The novel cross-feature hybrid associative prior network (CFHAPNet) with cross-attention and enhanced loss function improves pulsar candidate screening performance.

## Key findings

- CFHAPNet achieves 97.5% accuracy, 98.4% recall, and 98.0% F1-score on the FAST dataset.
- Ablation studies show proposed enhancements improve performance by approximately 5.6%.
- The model balances recognition precision and computational efficiency for large-scale pulsar surveys.

## Abstract

To enhance pulsar candidate recognition performance and improve model generalization, this paper proposes the cross-feature hybrid associative prior network (CFHAPNet). CFHAPNet incorporates a novel architecture and strategies to integrate multi-class heterogeneous feature subimages from each candidate into multi-channel data processing. By implementing cross-attention mechanisms and other enhancements for multi-view feature interactions, the model significantly strengthens its ability to capture fine-grained image texture details and weak prior semantic information. Through comparative analysis of feature weight similarity between subimages and average fusion weights, CFHAPNet efficiently identifies and filters genuine pulsar signals from candidate images collected across astronomical observatories. Additionally, refinements to the original loss function enhance convergence, further improving recognition accuracy and stability. To validate CFHAPNet’s efficacy, we compare its performance against several state-of-the-art methods on diverse datasets. The results demonstrate that under similar data scales, our approach achieves superior recognition performance. Notably, on the FAST dataset, the accuracy, recall, and F1-score reach 97.5%, 98.4%, and 98.0%, respectively. Ablation studies further reveal that the proposed enhancements improve overall recognition performance by approximately 5.6% compared to the original architecture, achieving an optimal balance between recognition precision and computational efficiency. These improvements make CFHAPNet a strong candidate for future large-scale pulsar surveys using new sensor systems.