Deep Image: Scaling up Image Recognition

2015/01/13 by Ren Wu, Wu Ren, Shengen Yan +8 · 1 voice · 330 citations
Computer Science · Mathematics · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Artificial intelligence #Computer science #Computer vision #Geometry #Human Pose and Action Recognition #Image (mathematics) #Mathematics #Pattern recognition (psychology) #Scaling #cs.CV

paper · pdf · doi:10.48550/arxiv.1501.02876

published in arXiv (Cornell University) (Cornell University) · This paper has been withdrawn by the authors due to a mistake related to ImageNet server submissions

openalex publication_date 2015/01/13 · arxiv created 2015/07/06 · arxiv updated 2015/07/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Deep convolutional filter banks for texture recognition and segmentation
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• ImageNet classification with deep convolutional neural networks
• Bilinear CNNs for Fine-grained Visual Recognition
• Deep Blue

Cited by

• 8-Bit Approximations for Parallelism in Deep Learning
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices
• Optimizing Network Performance for Distributed DNN Training on GPU Clusters: ImageNet/AlexNet Training in 1.5 Minutes
• Stanza: Layer Separation for Distributed Training in Deep Learning
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Deep Learning with Limited Numerical Precision
• Lets keep it simple, Using simple architectures to outperform deeper and\n more complex architectures
• Social Media Image Analysis for Public Health
• Learning Fine-grained Features via a CNN Tree for Large-scale Classification
• Recognition from Hand Cameras
• The Penalty Imposed by Ablated Data Augmentation
• Efficient Multi-Person Pose Estimation with Provable Guarantees
• Improved Regularization of Convolutional Neural Networks with Cutout
• dMath: A Scalable Linear Algebra and Math Library for Heterogeneous GP-GPU Architectures
• A Survey on Large-scale Machine Learning
• Cross-Domain Image Classification through Neural-Style Transfer Data Augmentation
• Targeted Nonlinear Adversarial Perturbations in Images and Videos
• Distributed Deep Learning Using Synchronous Stochastic Gradient Descent
• Online Hyper-parameter Learning for Auto-Augmentation Strategy
• Learning from Learning Machines: Optimisation, Rules, and Social Norms
• Context Augmentation for Convolutional Neural Networks
• Learning scale-variant and scale-invariant features for deep image classification
• Action Recognition using Visual Attention
• Hardware Synthesis of State-Space Equations; Application to FPGA Implementation of Shallow and Deep Neural Networks
• Parle: parallelizing stochastic gradient descent
• Deep Sequence Learning for Video Anticipation: From Discrete and Deterministic to Continuous and Stochastic
• Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign Recognition
• Is Saki #delicious? The Food Perception Gap on Instagram and Its Relation to Health
• MGSim + MGMark: A Framework for Multi-GPU System Research

Discussions

• Deep Image: Scaling Up Image Recognition [hn, 21 points, 5 comments]

Related

• Optimal Approach for Image Recognition using Deep Convolutional Architecture
• Some Improvements on Deep Convolutional Neural Network Based Image Classification
• Deep Learning for Image Super-resolution: A Survey
• Deep Learning for Image Super-Resolution: A Survey
• Efficient High-Resolution Deep Learning: A Survey