Multi-task, multi-domain learning: Application to semantic segmentation and pose regression.
Damien FourureRémi EmonetÉlisa FromontDamien MuseletNatalia NeverovaAlain TrémeauChristian WolfPublished in: Neurocomputing (2017)
Keyphrases
- multi task
- multi task learning
- learning tasks
- multi domain
- learning problems
- weakly supervised
- learning process
- data sets
- reinforcement learning
- supervised learning
- domain specific
- semantic segmentation
- cross domain
- superpixels
- topic models
- machine learning algorithms
- semi supervised learning
- unsupervised learning
- general purpose
- d objects
- hidden markov models
- active learning
- prior knowledge
- multiscale
- training data
- computer vision
- learning algorithm