generative adversarial network

Pitfalls of Training Generative Models for Video: From Mode Collapse to Unstable Dynamics

This paper analyzes common pitfalls encountered during video GAN training and explores methods to mitigate them through hybrid loss functions. We focus on combining adversarial, pixel-wise reconstruction, perceptual, and temporal consistency losses to stabilize learning and improve the realism and coherence of generated video. An empirical study compares several loss configurations on a human action video dataset, using PSNR, LPIPS, FVD, and a custom temporal consistency metric.

Recommendation systems techniques based on generative models and matrix factorization: a survey

Collaborative filtering (CF) is a technique that can filter out items that a user might like based on the behaviors and preferences of similar users.  It is a key en-abler technique for an effective recommendation system (RS).  Model-based recommendation systems, a subset of CF, use data, typically ratings, to construct models for providing personalized suggestions to users.  Our objective in this work is to provide a comprehensive overview of various techniques employed in Model-based RS, focusing on their theoretical foundations and practical applications.  We explore

SYNTHESIS OF BIOMEDICAL IMAGES BASED ON GENERATIVE ADVERSARIAL NETWORKS

Mo­dern da­ta­ba­ses of bi­ome­di­cal ima­ges ha­ve be­en in­ves­ti­ga­ted. Bi­ome­di­cal ima­ging has be­en shown to be ex­pen­si­ve and ti­me con­su­ming. A da­ta­ba­se of ima­ges of pre­can­ce­ro­us and can­ce­ro­us bre­asts "BPCI2100" was de­ve­lo­ped. The da­ta­ba­se con­sists of 2,100 ima­ge fi­les and a MySQL da­ta­ba­se of me­di­cal re­se­arch in­for­ma­ti­on (pa­ti­ent in­for­ma­ti­on and ima­ge fe­atu­res). Ge­ne­ra­ti­ve ad­ver­sa­ri­al net­works (GAN) ha­ve be­en fo­und to be an ef­fec­ti­ve me­ans of ima­ge ge­ne­ra­ti­on.