Beyond still images: Temporal features and input variance resilience

원문 초록

Traditionally, vision models have predominantly relied on spatial features extracted from static images, deviating from the continuous stream of spatiotemporal features processed by the brain in natural vision. While numerous video-understanding models have emerged, incorporating videos into image-understanding models with spatiotemporal features has been limited. Drawing inspiration from natural vision, which exhibits remarkable resilience to input changes, our research focuses on the development of a brain-inspired model for vision understanding trained with videos. Our findings demonstrate that models that train on videos instead of still images and include temporal features become more resilient to various alternations on input media.