Deep Image: Scaling up Image Recognition
This work addresses the problem of improving image recognition performance for computer vision applications, representing an incremental advancement through optimized scaling.
The paper tackled scaling up image recognition by developing Deep Image, an end-to-end deep learning system, achieving state-of-the-art results on multiple computer vision benchmarks.
We present 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 multi-scale high-resolution images. Our method achieves excellent results on multiple challenging computer vision benchmarks.