I - Introduction II - Preliminaries III - Different levels of supervision III.1. Different supervisions III.2. Priors. III.2.a Knowledge driven priors III.
2.b Data driven priors IV - A unified view V - Semi-supervised learning V.1. Introduction to the setting. V.2. Adversarial learning V.3.
Consistency regularization V.4. Unsupervised representation learning V.5. Self-paced learning. V.6. Mixed-supervision.
V.7. Invited chapter. VI - Unsupervised domain adaptation VI.1. Introduction to the setting. VI.2.
Adversarial learning. VI.3. Source-free adaptation. VI.4. Domain generalization? VI.5.
Invited chapter. VII - Weakly supervised segmentation VII.1. Introduction to the setting. VII.2. From global cues to pixel labels VII.3.
Constrained CNNs VII.3.a Equality constraints. VII.3.b Constrained CNNs: Inequality constraints. VII.4.
Class activation maps based methods. VII.5. Invited chapter/s VIII - Few-shot learning VIII.1. Introduction to the setting. VIII.2.
Learning to learn. VIII.3. Data augmentation. VIII.4. Simple baselines. VIII.
5. Invited chapter IX - Unsupervised segmentation IX.1. Introduction to the setting. IX.2. Auto-encoders IX.3.
Use of the gradient IX.4. Leveraging constraints IX.5. Invited chapter X - Perspectives and future directions.