Gradient Forward-Propagation for Large-Scale Temporal Video Modelling release_jualyispircjzntv35bkpcx7jq

by Mateusz Malinowski and Dimitrios Vytiniotis and Grzegorz Swirszcz and Viorica Patraucean and Joao Carreira

Released as a article .

2021  

Abstract

How can neural networks be trained on large-volume temporal data efficiently? To compute the gradients required to update parameters, backpropagation blocks computations until the forward and backward passes are completed. For temporal signals, this introduces high latency and hinders real-time learning. It also creates a coupling between consecutive layers, which limits model parallelism and increases memory consumption. In this paper, we build upon Sideways, which avoids blocking by propagating approximate gradients forward in time, and we propose mechanisms for temporal integration of information based on different variants of skip connections. We also show how to decouple computation and delegate individual neural modules to different devices, allowing distributed and parallel training. The proposed Skip-Sideways achieves low latency training, model parallelism, and, importantly, is capable of extracting temporal features, leading to more stable training and improved performance on real-world action recognition video datasets such as HMDB51, UCF101, and the large-scale Kinetics-600. Finally, we also show that models trained with Skip-Sideways generate better future frames than Sideways models, and hence they can better utilize motion cues.
In text/plain format

Archived Files and Locations

application/pdf  12.0 MB
file_mvztank5ifc2thjbzagjzdnp5e
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-06-15
Version   v1
Language   en ?
arXiv  2106.08318v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: e99c1030-f328-40b1-b050-cbd641adf8b3
API URL: JSON