UNet

ARCHITECTURE FOR HIGH-LOAD WEB RESOURCES OPTIMIZATION

The large amount of data used on web resources contributes to their slowdown, which negatively affects the loading time and the overall impression of the work. Caching servers, which temporarily store frequently requested data closer to the user, can significantly reduce the response time of servers, reduce the load on the primary computing resources, and increase the stability of web applications. Their implementation becomes especially relevant in the case of highly loaded web services.

Improving pedestrian segmentation using region proposal-based CNN semantic segmentation

Pedestrian segmentation is a critical task in computer vision, but it can be challenging for segmentation models to accurately classify pedestrians in images with challenging backgrounds and luminosity changes, as well as occlusions.  This challenge is further compounded for compressed models that were designed to deal with the high computational demands of deep neural networks.  To address these challenges, we propose a novel approach that integrates a region proposal-based framework into the segmentation process.  To evaluate the performance of the proposed framework,