Statements (103)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:neural_networks
|
| gptkbp:adapted_into |
various tasks
|
| gptkbp:applies_to |
computer vision
|
| gptkbp:can_be_combined_with |
attention mechanisms
other architectures top-down and bottom-up pathways |
| gptkbp:designed_for |
object detection
|
| gptkbp:developed_by |
gptkb:Kaiming_He
research institutions |
| gptkbp:enhances |
semantic segmentation
|
| gptkbp:has_achieved |
state-of-the-art results
state-of-the-art performance |
| https://www.w3.org/2000/01/rdf-schema#label |
feature pyramid networks
|
| gptkbp:improves |
multi-scale feature representation
feature representation |
| gptkbp:introduced |
Lin et al.
|
| gptkbp:is_adopted_by |
gptkb:medical_imaging
gptkb:robotics research papers augmented reality self-driving cars video analysis |
| gptkbp:is_based_on |
pyramid pooling module
feature pyramids |
| gptkbp:is_beneficial_for |
real-time detection
|
| gptkbp:is_cited_in |
academic literature
|
| gptkbp:is_compared_to |
single-shot detectors
|
| gptkbp:is_compatible_with |
transfer learning
fine-tuning |
| gptkbp:is_described_as |
research articles
|
| gptkbp:is_documented_in |
Git Hub repositories
|
| gptkbp:is_enhanced_by |
attention mechanisms
|
| gptkbp:is_evaluated_by |
gptkb:Open_Images_dataset
gptkb:PASCAL_VOC gptkb:Pascal_VOC gptkb:COCO_dataset gptkb:Cityscapes_dataset gptkb:KITTI_dataset gptkb:ADE20_K_dataset gptkb:YOLO_models cross-validation LFW dataset m AP metric |
| gptkbp:is_implemented_in |
gptkb:Tensor_Flow
gptkb:Py_Torch |
| gptkbp:is_influenced_by |
gptkb:Na'vi
Feature Pyramid feature extraction techniques |
| gptkbp:is_integrated_with |
cloud computing platforms
|
| gptkbp:is_known_for |
high accuracy
modularity scalable architecture flexibility in architecture robustness to scale variations |
| gptkbp:is_optimized_for |
real-time applications
high-resolution images |
| gptkbp:is_part_of |
gptkb:Faster_R-CNN
AI applications deep learning frameworks image processing pipelines object recognition systems |
| gptkbp:is_popular_in |
deep learning community
|
| gptkbp:is_related_to |
gptkb:Artificial_Intelligence
gptkb:machine_learning gptkb:Res_Net gptkb:Retina_Net gptkb:Na'vi deep learning convolutional neural networks |
| gptkbp:is_scalable |
large datasets
|
| gptkbp:is_supported_by |
gptkb:scientific_community
community contributions academic papers open-source implementations hardware accelerators |
| gptkbp:is_tested_for |
benchmark datasets
|
| gptkbp:is_used_for |
image segmentation
object localization |
| gptkbp:is_used_in |
gptkb:medical_imaging
gptkb:vehicles augmented reality image classification video analysis image segmentation scene understanding face detection object tracking instance segmentation |
| gptkbp:is_utilized_in |
gptkb:robotics
security systems surveillance systems e-commerce applications |
| gptkbp:published_in |
gptkb:2017
|
| gptkbp:supports |
real-time applications
feature reuse |
| gptkbp:training |
backpropagation
|
| gptkbp:used_for |
object detection
|
| gptkbp:utilizes |
lateral connections
top-down pathway multi-scale features |
| gptkbp:year_established |
gptkb:2017
|
| gptkbp:bfsParent |
gptkb:Deep_Lab_v3+
|
| gptkbp:bfsLayer |
6
|