Functional near-infrared spectroscopy (fNIRS) is a non-invasive technique for monitoring brain activity. To better understand the brain, researchers often use deep learning to address the classification challenges of fNIRS data. Our study shows that while current networks in fNIRS are highly accurate for predictions within their training distribution, they falter at identifying and excluding abnormal data which is out-ofdistribution, affecting their reliability. We propose integrating metric learning and supervised methods into fNIRS research to improve networks capability in identifying and excluding out-of-distribution outliers. This method is simple yet effective. In our experiments, it significantly enhances the performance of various networks in fNIRS, particularly transformer-based one, which shows the great improvement in reliability. We will make our experiment data available on GitHub.