Large-Scale Deep Learning on the YFCC100M Dataset
arXiv:1502.03409
Abstract
We present a work-in-progress snapshot of learning with a 15 billion parameter deep learning network on HPC architectures applied to the largest publicly available natural image and video dataset released to-date. Recent advancements in unsupervised deep neural networks suggest that scaling up such networks in both model and training dataset size can yield significant improvements in the learning of concepts at the highest layers. We train our three-layer deep neural network on the Yahoo! Flickr Creative Commons 100M dataset. The dataset comprises approximately 99.2 million images and 800,000 user-created videos from Yahoo's Flickr image and video sharing platform. Training of our network takes eight days on 98 GPU nodes at the High Performance Computing Center at Lawrence Livermore National Laboratory. Encouraging preliminary results and future research directions are presented and discussed.
Cited by in corpus (6)
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
- Quantifying Facial Age by Posterior of Age Comparisons
- Learning Visual Features from Large Weakly Supervised Data
- GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation
- The Helmholtz Method: Using Perceptual Compression to Reduce Machine Learning Complexity
- Improving Shape Deformation in Unsupervised Image-to-Image Translation