PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds.
Zhaoqi LengShuyang ChengBenjamin CaineWeiyue WangXiao ZhangJonathon ShlensMingxing TanDragomir AnguelovPublished in: ECCV (31) (2022)
Keyphrases
- unlabeled data
- labeled data
- labeled and unlabeled data
- point cloud
- supervised learning
- learning algorithm
- training data
- data points
- active learning
- semi supervised
- prior knowledge
- semi supervised learning
- training examples
- learning process
- data analysis
- labeled training data
- data sets
- machine learning
- background knowledge
- co training
- positive examples
- semi supervised classification
- supervised learning algorithms
- text classification
- reinforcement learning
- laser scanner
- labeled instances
- unsupervised learning
- multi view
- high dimensional data
- missing data
- structure from motion
- viewpoint
- training set