# Deep Image: Scaling up Image Recognition

arXiv: https://arxiv.org/abs/1501.02876 · HTML: https://mlsanity.com/paper/1501.02876/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2015.

## Built on by (most cited first, 16 of 16)

- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification](https://mlsanity.com/paper/2102.01284/) (2021)
- [Reconsidering CO2 emissions from Computer Vision](https://mlsanity.com/paper/2104.08702/) (2021)
- [GMF: General Multimodal Fusion Framework for Correspondence Outlier Rejection](https://mlsanity.com/paper/2211.00207/) (2022)
- [A New Frontier of AI: On-Device AI Training and Personalization](https://mlsanity.com/paper/2206.04688/) (2022)
- [Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification](https://mlsanity.com/paper/2101.02353/) (2021)
- [Generalization Gap in Data Augmentation: Insights from Illumination](https://mlsanity.com/paper/2404.07514/) (2024)
- [DelBugV: Delta-Debugging Neural Network Verifiers](https://mlsanity.com/paper/2305.18558/) (2023)
- [A Dynamic Weighted Tabular Method for Convolutional Neural Networks](https://mlsanity.com/paper/2205.10386/) (2022)
- [A Comprehensive Survey of Natural Language Generation Advances from the Perspective of Digital Deception](https://mlsanity.com/paper/2208.05757/) (2022)
- [Explainability Guided Multi-Site COVID-19 CT Classification](https://mlsanity.com/paper/2103.13677/) (2021)
- [Hardware Synthesis of State-Space Equations; Application to FPGA Implementation of Shallow and Deep Neural Networks](https://mlsanity.com/paper/2105.07131/) (2021)
- [What augmentations are sensitive to hyper-parameters and why?](https://mlsanity.com/paper/2111.03861/) (2021)
- [Video Intelligence as a component of a Global Security system](https://mlsanity.com/paper/2201.04349/) (2022)
- [ScaleNet: An Unsupervised Representation Learning Method for Limited Information](https://mlsanity.com/paper/2310.02386/) (2023)
- [The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentations](https://mlsanity.com/paper/2312.11309/) (2023)

## Abstract (arXiv)

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.