Cultivating DNN Diversity for Large Scale Video Labelling

07/13/2017
by   Mikel Bober-Irizar, et al.
0

We investigate factors controlling DNN diversity in the context of the Google Cloud and YouTube-8M Video Understanding Challenge. While it is well-known that ensemble methods improve prediction performance, and that combining accurate but diverse predictors helps, there is little knowledge on how to best promote & measure DNN diversity. We show that diversity can be cultivated by some unexpected means, such as model over-fitting or dropout variations. We also present details of our solution to the video understanding problem, which ranked #7 in the Kaggle competition (competing as the Yeti team).

READ FULL TEXT
research
06/14/2017

Deep Learning Methods for Efficient Large Scale Video Labeling

We present a solution to "Google Cloud and YouTube-8M Video Understandin...
research
07/03/2018

Deep Architectures and Ensembles for Semantic Video Classification

This work addresses the problem of accurate semantic labelling of short ...
research
06/26/2017

YouTube-8M Video Understanding Challenge Approach and Applications

This paper introduces the YouTube-8M Video Understanding Challenge hoste...
research
06/26/2017

An Effective Way to Improve YouTube-8M Classification Accuracy in Google Cloud Platform

Large-scale datasets have played a significant role in progress of neura...
research
08/21/2018

Constrained-size Tensorflow Models for YouTube-8M Video Understanding Challenge

This paper presents our 10th place solution to the second YouTube-8M vid...
research
06/02/2022

Mask-Guided Divergence Loss Improves the Generalization and Robustness of Deep Neural Network

Deep neural network (DNN) with dropout can be regarded as an ensemble mo...
research
06/04/2018

Sloth Search System at the Video Browser Showdown 2018 - Final Notes

This short paper provides further details of the Sloth Search System, wh...

Please sign up or login with your details

Forgot password? Click here to reset