- Getting started
- Introduction
- Overview of topics
- How to contribute
- General best practices
- Model families
- Classifier / Tagger
- Semantic Segmentor
- Object Detector
- Instance Segmentor
- Attributor
- Model architectures
- ResNet
- Faster R-CNN
- Mask R-CNN
- DeepLabv3+
- U-Net
- FBNetV3
- U-Net++
- Efficient Net
- PAN
- PSPNet
- LinkNet
- FPN
- RetinaNet
- Cascade RCNN
- FBNetV3IS
- FBNetV3OD
- CascadeMask R-CNN
- Metrics
- Confusion Matrix
- Intersection over Union (IoU)
- Accuracy
- Hamming score
- Precision
- Recall
- Precision-Recall curve and AUC-PR
- F-beta score
- Average Precision
- mean Average Precision (mAP)
- Loss
- Cross-Entropy Loss
- Binary Cross-Entropy Loss
- Focal loss
- Bounding Box Regression Loss
- CrossEntropyIoULoss2D
- Solvers / Optimizers
- Epsilon Coefficient
- Momentum (SGD)
- Adam
- Adadelta
- Adagrad
- AdaMax
- Adamw
- ASGD
- Base Learning Rate
- Rprop
- RMSprop
- SGD
- Weight Decay
- Training Parameters
- Patience
- Min delta
- Seed
- Batch Size
- Iterations
- Epoch
- Scheduler
- Warm-up
- CyclicLR
- MultiStepLR
- StepLR
- CosineAnnealingLR
- ReduceLROnPlateau
- ExponentialLR
- Augmentations
- Horizontal Flip
- Vertical Flip
- Random Crop
- Random Sized Crop
- Rotate
- Resize
- Blur
- Smallest max size
- Center Crop
- Color Jitter
- Gaussian Noise
- Shift Scale Rotate
- Longest Max Size
- Equalize
- To gray
- Shear
- Mosaic
- Copy Paste
- Deployment
- Primitive deployment using web frameworks
- Commonly used web frameworks
- Containerized Deployment
- Orchestrated Deployment
- Challenges of Deployment
- Splits
- General Information
- Random
- Stratification
- MP WIKI
- MODEL FAMILIES
- ATTRIBUTOR
Attributor
Attributors are used in combination with other models such as object detectors, semantic and instance segmentors.
They add a layer of meta-data to your model. First, a detection or segmentation model creates predictions, and then the attributor runs another classification on top of this prediction. Chaining the models this way allows you to break down a task into smaller sub-tasks, which often yields better results.
A good example use case for attributors is defect detection in manufacturing. Often, first, an instance segmentor is trained to find a defect, and then an attributor assesses its severity.
When annotating data, attributes can also be used to create second-degree taxonomies:
Further Resources
Last updated on Jun 01, 2022