Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection.
Ismail EleziZhiding YuAnima AnandkumarLaura Leal-TaixéJose M. AlvarezPublished in: CVPR (2022)
Keyphrases
- object detection
- training set
- training examples
- labeling effort
- object categories
- object detectors
- image labeling
- labeling process
- semantic segmentation
- labeling scheme
- active learning
- manual labeling
- labeled images
- labeling problems
- image parsing
- label propagation
- discriminatively trained
- training process
- training data
- ground truth labels
- boosted classifiers
- test set
- pairwise
- computer vision
- pascal voc
- face recognition
- object recognition
- class labels
- object classification
- face detection
- machine learning
- feature selection
- unsupervised learning
- training samples
- background subtraction
- structured prediction
- total cost
- object class
- scene understanding