F2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptation.
Yuting WangRicardo GuerreroVladimir PavlovicPublished in: WACV (2023)
Keyphrases
- domain adaptation
- weakly supervised
- learning objects
- object detection
- object class
- semi supervised
- object detectors
- object segmentation
- object categories
- superpixels
- multiple sources
- multi class
- object recognition
- computer vision
- metadata
- learning process
- semi supervised learning
- transfer learning
- cross domain
- labeled data
- e learning
- training data
- topic models
- unlabeled data
- multi view
- object classes
- co training
- knowledge transfer
- unsupervised learning
- semantic relations
- data sets
- general purpose
- supervised learning
- active learning
- viewpoint
- multiscale
- data mining