Image Net Large Scale Visual Recognition Challenge
GPTKB entity
Statements (106)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:competition
gptkb:Computer_Vision gptkb:Artificial_Intelligence |
| gptkbp:associated_with |
gptkb:Artificial_Intelligence
gptkb:academic_conferences gptkb:cloud_computing gptkb:open-source_software gptkb:machine_learning commercial use big data data collection research papers data preprocessing algorithm development community contributions ethical considerations high-performance computing hyperparameter tuning real-world applications data science model evaluation privacy concerns collaborative research AI safety benchmarking data augmentation data normalization object detection social impact software engineering model deployment feature extraction explainable AI crowdsourcing image segmentation convolutional neural networks model training model testing data labeling bias in AI future of AI GPU computing deep neural networks |
| gptkbp:challenges |
Ambiguity in Questions
Complexity of Visual Data Integration of Vision and Language |
| gptkbp:class |
1000
|
| gptkbp:contributed_to |
transfer learning
|
| gptkbp:developed_by |
Research Institutions
Tech Companies |
| gptkbp:evaluates |
Accuracy
F1 Score Precision Recall top-5 accuracy |
| gptkbp:field |
computer vision
|
| gptkbp:first_held |
gptkb:2010
|
| gptkbp:frequency |
annual
|
| gptkbp:goal |
image classification
|
| gptkbp:has_applications_in |
gptkb:Natural_Language_Processing
Human-Computer Interaction Image Understanding |
| gptkbp:has_artwork |
over 14 million
|
| gptkbp:has_method |
gptkb:neural_networks
gptkb:Deep_Learning gptkb:Recurrent_Neural_Networks Attention Mechanisms |
| https://www.w3.org/2000/01/rdf-schema#label |
Image Net Large Scale Visual Recognition Challenge
|
| gptkbp:impact |
gptkb:AI_technology
|
| gptkbp:influenced |
Image classification models
|
| gptkbp:is_evaluated_by |
Human Judgments
Automated Metrics |
| gptkbp:is_explored_in |
gptkb:Workshops
Conferences Academic Research |
| gptkbp:is_related_to |
Image Captioning
Visual Reasoning Multimodal Learning |
| gptkbp:is_supported_by |
gptkb:Libraries
Frameworks Open Source Tools |
| gptkbp:is_used_in |
gptkb:Autonomous_Vehicles
gptkb:robotics Healthcare |
| gptkbp:last_held |
gptkb:2020
|
| gptkbp:location |
online
|
| gptkbp:notable_achievement |
Advancement of deep learning
|
| gptkbp:notable_winner |
gptkb:Inception
gptkb:Dense_Net gptkb:Res_Net gptkb:VGGNet gptkb:Alex_Net |
| gptkbp:organizer |
gptkb:Stanford_University
|
| gptkbp:participants |
gptkb:researchers
|
| gptkbp:provides_information_on |
gptkb:Image_Net
gptkb:CLEVR_Dataset GQA Dataset VQA Dataset |
| gptkbp:sponsor |
gptkb:Google
|
| gptkbp:trends |
Improved Accuracy
Real-time Processing Enhanced User Interaction Broader Applications Integration with AR/ VR |
| gptkbp:bfsParent |
gptkb:Ali_Farhadi
|
| gptkbp:bfsLayer |
4
|