Deep Residual Learning for Image Recognition
GPTKB entity
Statements (51)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
Research Paper
|
| gptkbp:addresses |
Degradation problem in deep networks
|
| gptkbp:analyzes |
Network architectures
|
| gptkbp:appliesTo |
Computer_Vision
|
| gptkbp:author |
gptkb:Kaiming_He
|
| gptkbp:citedBy |
Over 10000 times
|
| gptkbp:completed |
State-of-the-art performance
|
| gptkbp:contains |
Experimental results
|
| gptkbp:designedBy |
Identity mapping
|
| gptkbp:developedBy |
gptkb:Microsoft_Research
|
| gptkbp:enhances |
Feature extraction
|
| gptkbp:exhibits |
Better accuracy with deeper networks
|
| gptkbp:focusesOn |
Image Recognition
|
| gptkbp:hasCollaboratedWith |
Other research institutions
|
| https://www.w3.org/2000/01/rdf-schema#label |
Deep Residual Learning for Image Recognition
|
| gptkbp:improves |
Training of deep neural networks
|
| gptkbp:includes |
gptkb:ImageNet_dataset
|
| gptkbp:influences |
Subsequent research in deep learning
|
| gptkbp:introduced |
Residual_Networks_(ResNets)
|
| gptkbp:involves |
Optimization techniques
|
| gptkbp:isAssociatedWith |
Kaiming_He's_work
|
| gptkbp:isAttendedBy |
Industry applications
|
| gptkbp:isChallengedBy |
Deep learning models
|
| gptkbp:isCitedIn |
Numerous academic papers
|
| gptkbp:isDiscussedIn |
Machine learning conferences
|
| gptkbp:isEvaluatedBy |
Various benchmarks
|
| gptkbp:isExploredIn |
PhD_theses
|
| gptkbp:isInfluencedBy |
AI development
|
| gptkbp:isLocatedIn |
gptkb:PyTorch
TensorFlow |
| gptkbp:isPartOf |
Computer_Vision_research
Deep_Learning_literature |
| gptkbp:isPublishedIn |
IEEE
|
| gptkbp:isRecognizedBy |
AI community
|
| gptkbp:isRecognizedFor |
Innovative architecture
|
| gptkbp:isSupportedBy |
Funding agencies
Large-scale datasets |
| gptkbp:isTrainedIn |
Various datasets
|
| gptkbp:isUsedIn |
Image classification tasks
Object detection tasks Semantic segmentation tasks |
| gptkbp:isUtilizedIn |
Real-time applications
|
| gptkbp:keyIssues |
Deep learning advancements
|
| gptkbp:provides |
Theoretical insights
|
| gptkbp:publishedIn |
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
|
| gptkbp:relatedTo |
gptkb:Convolutional_Neural_Networks
Traditional deep networks |
| gptkbp:supports |
Transfer learning
|
| gptkbp:uses |
Skip connections
|
| gptkbp:utilizes |
Batch normalization
|
| gptkbp:year |
2016
|