UP-DETR: Unsupervised Pre-Training for Object Detection With Transformers.
Zhigang DaiBolun CaiYugeng LinJunying ChenPublished in: CVPR (2021)
Keyphrases
- object detection
- supervised learning
- supervised training
- discriminatively trained
- data driven
- deep architectures
- training algorithm
- semi supervised
- face detection
- boosted classifiers
- neural network
- training process
- real time
- unsupervised learning
- scene understanding
- object classification
- training samples
- training set
- machine learning
- data sets
- multi class
- feature space
- decision trees
- human detection
- restricted boltzmann machine
- e learning
- genetic algorithm
- deformable part models