Essentials for few-shot learning on images (B04)

• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
• Term: since 2023
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 499552394

The core principle of few-shot learning is to build on visual feature representations obtained by pre-training neural networks on large image datasets and transfer the learned representation to recognize new object classes from a few samples. We will develop novel core algorithms for few-shot learning, including analysis of the properties of base representations, matching strategies, generative techniques to learn residual features for distinguishing new objects, and techniques for incrementally learning new classes without forgetting previous knowledge.

• DFG Programme: Collaborative Research Centres
• Subproject of: SFB 1597: Small Data
• Applicant Institution: Albert-Ludwigs-Universität Freiburg
• Project Heads: Professor Dr.-Ing. Thomas Brox; Professor Dr. Abhinav Valada