A probabilistic representation for efficient large scale visual recognition tasks

CVPR 2011 ◽  
2011 ◽  
Author(s):  
Subhabrata Bhattacharya ◽  
Rahul Sukthankar ◽  
Rong Jin ◽  
Mubarak Shah
Keyword(s):  
Large Scale ◽  
Visual Recognition ◽  
Probabilistic Representation

scholarly journals HD-MTL: Hierarchical Deep Multi-Task Learning for Large-Scale Visual Recognition

2017 ◽  
Vol 26 (4) ◽  
pp. 1923-1938 ◽  
Author(s):  
Jianping Fan ◽  
Tianyi Zhao ◽  
Zhenzhong Kuang ◽  
Yu Zheng ◽  
Ji Zhang ◽  
...  
Keyword(s):  
Large Scale ◽  
Visual Recognition ◽  
Task Learning

scholarly journals Reliability of a Visual Recognition System for Detection of Johnsongrass(Sorghum halepense) in Corn

2011 ◽  
Vol 25 (4) ◽  
pp. 645-651 ◽  
Author(s):  
Dionisio Andújar ◽  
Ángela Ribeiro ◽  
Cesar Fernández-Quintanilla ◽  
José Dorado
Keyword(s):  
Large Scale ◽  
Visual Recognition ◽  
Visual Detection ◽  
Cropping Systems ◽  
Experimental Period ◽  
Recognition System ◽  
Infested Area ◽  
Net Returns ◽  
Cropping Season ◽  
Combine Harvester

The feasibility of visual detection of weeds for map-based patch spraying systems needs to be assessed for use in large-scale cropping systems. The main objective of this research was to evaluate the reliability and profitability of using maps of Johnsongrass patches constructed at harvest to predict spatial distribution of weeds during the next cropping season. Johnsongrass patches visually were assessed from the cabin of a combine harvester in three corn fields and were compared with maps obtained in the subsequent year prior to postemergence herbicide application. There was a good correlation (71% on average) between the position of Johnsongrass patches on the two maps (fall vs. spring). The highest correlation (82%) was obtained with relatively large infestations, whereas the lowest (58%) was obtained when the infested area was smaller. Although the relative positions of the patches remained almost unchanged from 1 yr to the next, the infested area increased in all fields during the 4-yr experimental period. According to our estimates, using a strategy based on spraying full rates of herbicides to patches recorded in the map generated in the previous fall resulted in higher net returns than spraying the whole field, either at full or half rate. This site-specific strategy resulted in an average 65% reduction in the volume of herbicide applied to control this weed.

scholarly journals Image Classification Using Transfer Learning and Deep Learning

2021 ◽  
Vol 10 (9) ◽  
pp. 25394-25398
Author(s):  
Chitra Desai
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Image Classification ◽  
Transfer Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Large Scale ◽  
Deep Neural Network ◽  
Visual Recognition ◽  
Classification Of Images

Deep learning models have demonstrated improved efficacy in image classification since the ImageNet Large Scale Visual Recognition Challenge started since 2010. Classification of images has further augmented in the field of computer vision with the dawn of transfer learning. To train a model on huge dataset demands huge computational resources and add a lot of cost to learning. Transfer learning allows to reduce on cost of learning and also help avoid reinventing the wheel. There are several pretrained models like VGG16, VGG19, ResNet50, Inceptionv3, EfficientNet etc which are widely used.   This paper demonstrates image classification using pretrained deep neural network model VGG16 which is trained on images from ImageNet dataset. After obtaining the convolutional base model, a new deep neural network model is built on top of it for image classification based on fully connected network. This classifier will use features extracted from the convolutional base model.

scholarly journals Evaluation of Pre-Trained Convolutional Neural Network Models for Object Recognition

2018 ◽  
Vol 7 (3.15) ◽  
pp. 95 ◽  
Author(s):  
M Zabir ◽  
N Fazira ◽  
Zaidah Ibrahim ◽  
Nurbaity Sabri
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Visual Recognition ◽  
Error Function ◽  
Network Models ◽  
Neural Network Models ◽  
California Institute Of Technology ◽  
Institute Of Technology ◽  
Similar Accuracy

This paper aims to evaluate the accuracy performance of pre-trained Convolutional Neural Network (CNN) models, namely AlexNet and GoogLeNet accompanied by one custom CNN. AlexNet and GoogLeNet have been proven for their good capabilities as these network models had entered ImageNet Large Scale Visual Recognition Challenge (ILSVRC) and produce relatively good results. The evaluation results in this research are based on the accuracy, loss and time taken of the training and validation processes. The dataset used is Caltech101 by California Institute of Technology (Caltech) that contains 101 object categories. The result reveals that custom CNN architecture produces 91.05% accuracy whereas AlexNet and GoogLeNet achieve similar accuracy which is 99.65%. GoogLeNet consistency arrives at an early training stage and provides minimum error function compared to the other two models. 

scholarly journals Dynamic connectivity analyses of intracranial EEG during recognition memory reveal various large-scale functional networks

2020 ◽  
Author(s):  
Jakub Kopal ◽  
Jaroslav Hlinka ◽  
Elodie Despouy ◽  
Luc Valton ◽  
Marie Denuelle ◽  
...  
Keyword(s):  
Recognition Memory ◽  
Large Scale ◽  
Visual Recognition ◽  
Effective Connectivity ◽  
Memory Task ◽  
Brain Regions ◽  
Neural Basis ◽  
Intracranial Eeg ◽  
Large Scale Networks ◽  
The Right

Recognition memory is the ability to recognize previously encountered events, objects, or people. It is characterized by its robustness and rapidness. Even this relatively simple ability requires the coordinated activity of a surprisingly large number of brain regions. These spatially distributed, but functionally linked regions are interconnected into large-scale networks. Understanding memory requires an examination of the involvement of these networks and the interactions between different regions while memory processes unfold. However, little is known about the dynamical organization of large-scale networks during the early phases of recognition memory. We recorded intracranial EEG, which affords high temporal and spatial resolution, while epileptic subjects performed a visual recognition memory task. We analyzed dynamic functional and effective connectivity as well as network properties. Various networks were identified, each with its specific characteristics regarding information flow (feedforward or feedback), dynamics, topology, and stability. The first network mainly involved the right visual ventral stream and bilateral frontal regions. It was characterized by early predominant feedforward activity, modular topology, and high stability. It was followed by the involvement of a second network, mainly in the left hemisphere, but notably also involving the right hippocampus, characterized by later feedback activity, integrated topology, and lower stability. The transition between networks was associated with a change in network topology. Overall, these results confirm that several large-scale brain networks, each with specific properties and temporal manifestation, are involved during recognition memory. Ultimately, understanding how the brain dynamically faces rapid changes in cognitive demand is vital to our comprehension of the neural basis of cognition.

Sign in / Sign up

Export Citation Format

Share Document