Baidu has a state -of-the-art image recognition system, Deep Image, developed using end-to-end deep learning. The key components are a custom-built supercomputer dedicated to deep learning, a highly optimized parallel algorithm using new strategies for data partitioning and communication, larger deep neural network models, novel data augmentation approaches, and usage of multiscale high-resolution images. On one of the most challenging computer vision benchmarks, the ImageNet classification challenge, our system has achieved the best result to date, with a top - 5 error rate of 5.98% -a relative 10.2% improvement over the previous best result.
Chinese search engine company Baidu says it has built the world’s most-accurate computer vision system, dubbed Deep Image, which runs on a supercomputer optimized for deep learning algorithms. Baidu's 5.98 percent error rate on the ImageNet object classification benchmark is better than Google's 2014 ImageNet competition winning 6.66 percent error rate.
In experiments, humans achieved an estimated error rate of 5.1 percent on the ImageNet dataset.
A sample of the effects Baidu used to augment images. Credit Baidu