.png){kind=icon}
Return
PreCNet: Next-Frame Video Prediction Based on Predictive Coding
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2023.3240857.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Predictive coding, currently a highly influential theory in neuroscience, has not been widely adopted in machine learning yet. In this work, we transform the seminal model of Rao and Ballard (1999) into a modern deep learning framework while remaining maximally faithful to the original schema. The resulting network we propose (PreCNet) is tested on a widely used next frame video prediction benchmark, which consists of images from an urban environment recorded from a car-mounted camera, and achieves state-of-the-art performance. Performance on all measures (MSE, PSNR, SSIM) was further improved when a larger training set (2M images from BDD100k), pointing to the limitations of the KITTI training set. This work demonstrates that an architecture carefully based in a neuroscience model, without being explicitly tailored to the task at hand, can exhibit exceptional performance.
Keywords:
Deep neural networks
next-frame video prediction
predictive coding
self-supervised learning
Journal
IF:
8.9
Papers:
7.6K
Citations:
7.2W
Organization
Cited Papers
ShareSaveShareSave
ShareSaveVariation in Mating Call Across the Hybrid Zone between the Fire-Bellied Toads Bombina bombina and B. variegata.png)
Evolution
EvolutionIF0
PREAI
ShareSaveShareSave
View more