ImageNet: Constructing a large-scale image database

Li, Feifei; Deng, Jia; Kai, Li

doi:10.1167/9.8.1037

Cited by 238 publications

(125 citation statements)

References 0 publications

Supporting

Mentioning

122

Contrasting

Unclassified

Order By: Relevance

“…Responses to natural images were then characterized by displaying static, grayscale images from the ImageNet database, which contains a wide variety of subjects including landscapes, objects, people, and animals (Fei-Fei et al, 2010). Each image was displayed for 100ms, separated by 400ms of spatially uniform illumination with intensity equal to the mean across all images ( Figure 1A).…”

Section: Resultsmentioning

confidence: 99%

Reconstruction of natural images from responses of primate retinal ganglion cells

Brackbill

Rhoades

Kling

et al. 2020

Preprint

View full text Add to dashboard Cite

The visual message conveyed by a retinal ganglion cell (RGC) is often summarized by its spatial receptive field, but in principle should also depend on other cells' responses and natural image statistics. To test this idea, linear reconstruction (decoding) of natural images was performed using combinations of responses of four high-density macaque RGC types, revealing consistent visual representations across retinas. Each cell's visual message, defined by the optimal reconstruction filter, reflected natural image statistics, and resembled the receptive field only when nearby, same-type cells were included. Reconstruction from each cell type revealed different and largely independent visual representations, consistent with their distinct properties. Stimulus-independent correlations primarily affected reconstructions from noisy responses. Nonlinear response transformation slightly improved reconstructions with either ON or OFF parasol cells, but not both. Inclusion of ON-OFF interactions enhanced reconstruction by emphasizing oriented edges, consistent with linear-nonlinear encoding models. Spatiotemporal reconstructions revealed similar spatial visual messages.

show abstract

Section: Resultsmentioning

confidence: 99%

Reconstruction of natural images from responses of primate retinal ganglion cells

Brackbill

Rhoades

Kling

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…This procedure should be applied in each work aimed at showing that a CAD system could help humans in evaluation. Pre-training the model before training it with the wrist bone images seem like a good procedure to adjust the parameters for the task, instead of using weights taken from a network that has been trained with a completely different dataset, e.g., ImageNet [12].…”

Section: Deep Neural Network Improves Fracture Detection By Cliniciansmentioning

confidence: 99%

X-Ray Bone Fracture Classification Using Deep Learning: A Baseline for Designing a Reliable Approach

et al. 2020

View full text Add to dashboard Cite

In recent years, bone fracture detection and classification has been a widely discussed topic and many researchers have proposed different methods to tackle this problem. Despite this, a universal approach able to classify all the fractures in the human body has not yet been defined. We aim to analyze and evaluate a selection of papers, chosen according to their representative approach, where the authors applied different deep learning techniques to classify bone fractures, in order to select the strengths of each of them and try to delineate a generalized strategy. Each study is summarized and evaluated using a radar graph with six values: area under the curve (AUC), test accuracy, sensitivity, specificity, dataset size and labelling reliability. Plus, we defined the key points which should be taken into account when trying to accomplish this purpose and we compared each study with our baseline. In recent years, deep learning and, in particular, the convolution neural network (CNN), has achieved results comparable to those of humans in bone fracture classification. Adopting a correct generalization, we are reasonably sure that a computer-aided diagnosis (CAD) system, correctly designed to assist doctors, would save a considerable amount of time and would limit the number of wrong diagnoses.

show abstract

“…(Chen et al 2015). In general, the framework consists of two parts: (1) fine-tuning the pre-trained CNN model, transfer the CNN pre-trained on the large-scale dataset ImageNet (Fei-Fei L et al 2009), and using the CNN for images feature extraction; (2) using XGBoost classifies the features to get the scene category of the images.…”

Section: Introductionmentioning

confidence: 99%

A Novel Framework for Remote Sensing Image Scene Classification

Jiang¹,

Zhao²,

Wu³

et al. 2018

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:High resolution remote sensing (HRRS) images scene classification aims to label an image with a specific semantic category. HRRS images contain more details of the ground objects and their spatial distribution patterns than low spatial resolution images. Scene classification can bridge the gap between low-level features and high-level semantics. It can be applied in urban planning, target detection and other fields. This paper proposes a novel framework for HRRS images scene classification. This framework combines the convolutional neural network (CNN) and XGBoost, which utilizes CNN as feature extractor and XGBoost as a classifier. Then, this framework is evaluated on two different HRRS images datasets: UC-Merced dataset and NWPU-RESISC45 dataset. Our framework achieved satisfying accuracies on two datasets, which is 95.57% and 83.35% respectively. From the experiments result, our framework has been proven to be effective for remote sensing images classification. Furthermore, we believe this framework will be more practical for further HRRS scene classification, since it costs less time on training stage.

show abstract

ImageNet: Constructing a large-scale image database

Cited by 238 publications

References 0 publications

Reconstruction of natural images from responses of primate retinal ganglion cells

Reconstruction of natural images from responses of primate retinal ganglion cells

X-Ray Bone Fracture Classification Using Deep Learning: A Baseline for Designing a Reliable Approach

A Novel Framework for Remote Sensing Image Scene Classification

Contact Info

Product

Resources

About