ImageNet statistics

Tool stats & trends

Looking to identify usage trends or leading experts?

ImageNet specifications

Information


Unique identifier OMICS_22938
Name ImageNet
Restrictions to use Academic or non-commercial use
Community driven No
Data access File download, Browse, Application programming interface
User data submission Not allowed
Maintained Yes
Wikipedia https://en.wikipedia.org/wiki/ImageNet

Publications for ImageNet

ImageNet citations

 (17)
library_books

Automated plant species identification—Trends and future directions

2018
PLoS Comput Biol
PMCID: 5886388
PMID: 29621236
DOI: 10.1371/journal.pcbi.1005993

[…] n Ocean and South American flora (in 2015) and the North African flora (in 2016). Since June 2015, [email protected] applies deep learning techniques for image classification. The network is pretrained on the ImageNet dataset and periodically fine-tuned on steadily growing [email protected] data. Joly et al. [] evaluated the [email protected] application, which supported the identification of 2,200 species at that time, and […]

library_books

Temporal and Fine Grained Pedestrian Action Recognition on Driving Recorder Database

2018
PMCID: 5855092
PMID: 29461473
DOI: 10.3390/s18020627

[…] a trajectory is sampled; they are incorporated into a feature vector.DeCAF. Activation features were extracted based on the AlexNet/VGG-16. In the paper, we set fc6 for each CNN architecture. We used ImageNet pre-trained model (ImageNet, ImageNet with VGG-16) [,], Places205 pre-trained model (Places205) [], and ImageNet + Places205 pre-trained model (HybridCNN) []. One more model, all combined (Im […]

library_books

Association of Pathological Fibrosis With Renal Survival Using Deep Neural Networks

2018
PMCID: 5932308
PMID: 29725651
DOI: 10.1016/j.ekir.2017.11.002

[…] During training, we resized each image to 299 × 299 pixels to make it compatible with the original dimensions of the Inception v3 network architecture and leveraged the image features learned by the ImageNet pretrained network. This procedure, known as transfer learning, is optimal, given the amount of data available.Figure 2Our deep neural network was trained using back-propagation. Using the fr […]

library_books

Retinal Lesion Detection With Deep Learning Using Image Patches

2018
PMCID: 5788045
PMID: 29372258
DOI: 10.1167/iovs.17-22721

[…] The object of interest in these images occupied a proportion of the total image that mimics that of the ImageNet dataset. Typically, between 5% and 50% of pixels belonged to the object of interest. A single CNN using the GoogLeNet architecture with a 128 × 128 × 3 input with a five-class output was cons […]

library_books

Real Time Monitoring and Analysis of Zebrafish Electrocardiogram with Anomaly Detection

2017
PMCID: 5796315
PMID: 29283402
DOI: 10.3390/s18010061

[…] (an open source neural network library written in Python) with a Tensorflow backend [,]. Google’s Inception v3 model was imported without its final layer and the model was configured with inception’s ImageNet pre-trained layer weights. The following layers were then added to the top of the inception architecture: a 2D global average pooling layer, two densely connected layers with 1024 and 256 par […]

library_books

Fine grained recognition of plants from images

2017
Plant Methods
PMCID: 5740928
PMID: 29299049
DOI: 10.1186/s13007-017-0265-4

[…] [] and our preliminary experiments show that this network architecture leads to results superior to other state-of-the-art CNN architectures. The publicly available [] Tensorflow model pretrained on ImageNet was used to initiate the parameters of convolutional layers. The main hyperparameters were set as follows:Optimizer: RMSProp with momentum 0.9 and decay 0.9.Weight decay: 0.00004.Learning rat […]

Citations

Looking to check out a full list of citations?

ImageNet institution(s)
Stanford University, Stanford, CA, USA; University of Michigan, Ann Arbor, MI, USA; Massachusetts Institute of Technology, Cambridge, MA, USA
ImageNet funding source(s)
Supported by Stanford University, UNC Chapel Hill, Google and Facebook.

ImageNet reviews

star_border star_border star_border star_border star_border
star star star star star

Be the first to review ImageNet