mlsanityData to 7 Oct 2026

Deep Image: Scaling up Image Recognition

arXiv 1501.02876 ↗First posted 13 Jan 2015cs.CVcited by 16

Not on the map. Why?

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.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jan 2015.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 5; 2023: 4; 2024: 1.

16 papers.

Sort:

  1. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  2. 2021Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classificationcited by 23
  3. 2021Reconsidering CO2 emissions from Computer Visioncited by 9
  4. 2022GMF: General Multimodal Fusion Framework for Correspondence Outlier Rejectioncited by 7
  5. 2022A New Frontier of AI: On-Device AI Training and Personalizationcited by 5
  6. 2021Low-cost and high-performance data augmentation for deep-learning-based skin lesion classificationcited by 4
  7. 2024Generalization Gap in Data Augmentation: Insights from Illuminationcited by 4
  8. 2023DelBugV: Delta-Debugging Neural Network Verifierscited by 3
  9. 2022A Dynamic Weighted Tabular Method for Convolutional Neural Networkscited by 1
  10. 2022A Comprehensive Survey of Natural Language Generation Advances from the Perspective of Digital Deceptioncited by 1
  11. 2021Explainability Guided Multi-Site COVID-19 CT Classificationcited by 0
  12. 2021Hardware Synthesis of State-Space Equations; Application to FPGA Implementation of Shallow and Deep Neural Networkscited by 0
4 more
  1. 2021What augmentations are sensitive to hyper-parameters and why?cited by 0
  2. 2022Video Intelligence as a component of a Global Security systemcited by 0
  3. 2023ScaleNet: An Unsupervised Representation Learning Method for Limited Informationcited by 0
  4. 2023The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentationscited by 0