Statements (61)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:neural_networks
|
| gptkbp:based_on |
Residual Learning
|
| gptkbp:competes_with |
gptkb:Dense_Net
gptkb:VGGNet |
| gptkbp:developed_by |
gptkb:Kaiming_He
|
| gptkbp:has |
gptkb:Batch_Normalization
Residual Blocks Multiple Depths |
| gptkbp:has_achieved |
State-of-the-art Performance
|
| https://www.w3.org/2000/01/rdf-schema#label |
Res Net Variants
|
| gptkbp:improves |
Training Speed
|
| gptkbp:includes |
gptkb:Res_Net-101
gptkb:Res_Net-152 gptkb:Res_Net-50 |
| gptkbp:influenced |
Subsequent Architectures
|
| gptkbp:introduced_in |
gptkb:2015
|
| gptkbp:is |
gptkb:test_subjects
gptkb:Open_Source Highly Scalable Modular Design Widely Used Flexible Architecture Deep Learning Architecture Used in Robotics Used in Augmented Reality Used in Virtual Reality Used in Mobile Applications Used in Medical Imaging Used in E-commerce Highly Efficient Used in Autonomous Vehicles Used in Facial Recognition Used in Video Analysis Benchmark Model End-to-End Trainable Feature Extractor Framework for Computer Vision Image Processing Tool Popular in Academia Popular in Industry Robust to Overfitting Standard in Competitions Used in Content Moderation Used in Industry Applications Used in Research Papers Used in Retail Analytics Used in Social Media Analysis Used in Sports Analytics Used in Surveillance Systems Widely Implemented |
| gptkbp:is_applied_in |
Object Detection
Semantic Segmentation |
| gptkbp:is_evaluated_by |
gptkb:Image_Net_Dataset
|
| gptkbp:is_optimized_for |
GPU Training
|
| gptkbp:is_trained_in |
Large Datasets
|
| gptkbp:reduces |
Vanishing Gradient Problem
|
| gptkbp:supports |
gptkb:stage_adaptation
|
| gptkbp:used_for |
Image Classification
|
| gptkbp:utilizes |
Skip Connections
|
| gptkbp:bfsParent |
gptkb:Deep_Residual_Learning_for_Image_Recognition
|
| gptkbp:bfsLayer |
5
|