In the task of person re-identification (re-ID), capturing the long-range dependency of instances is crucial for accurate identification. The existing methods excel at extracting local features but often overlook the global information of instance images. To address this limitation, we propose a convolution-based counterfactual learning framework, called PSF-C-Net, to focus on global information rather than local detailed features. PSF-C-Net adopts a parameter-sharing dual-path structure to perform counterfactual operations in the prediction space. It takes both the actual instance image and a counterfactual instance image that disrupts the contextual relationship as the input. The counterfactual framework enables the interpretable modeling of global features without introducing additional parameters. Additionally, we propose a novel method for generating counterfactual instance images, which effectively constructs an explicit counterfactual space, to reliably implement counterfactual strategies. We have conducted extensive experiments to evaluate the performance of PSF-C-Net on the Market-1501 and Duke-MTMC-reID datasets. The results demonstrate that PSF-C-Net achieves state-of-the-art performance.
Background: Early evaluation of treatment efficacy in adolescents and young adults with major depressive episodes (MDEs) remains a clinical challenge, often delaying timely therapeutic adjustments. Electroencephalography (EEG) alpha traveling waves, particularly those elicited by intermittent photic stimulation (IPS), may serve as biomarkers reflecting neural dynamics. This study aimed to investigate whether IPS-induced alpha traveling waves could predict early treatment outcomes in transitional-aged youth with MDEs. Methods: We recorded EEG signals from 119 patients aged 16–24 years at admission, prior to a standardized two-week treatment regimen. IPS was applied using multiple stimulus frequencies, and alpha traveling waves were analyzed in terms of directionality (forward vs. backward) and hemispheric lateralization. Results: Alpha traveling wave amplitudes varied across individuals, depending on stimulus frequency and hemisphere. Notably, a higher amplitude of backward alpha traveling waves at 10 Hz IPS in the left hemisphere significantly predicted positive early treatment response. In contrast, forward waves and right hemisphere responses did not show predictive value. Conclusions: IPS-induced backward alpha traveling waves in the left hemisphere may represent promising EEG biomarkers for early prediction of treatment efficacy in youth with MDEs. These findings offer a potential neurophysiological tool to support personalized treatment strategies and inform future clinical applications in adolescent and young adult depression.