Piecewise Classifier Mappings: Learning Fine-Grained Learners for Novel Categories With Few Examples
Abstract: Humans are capable of learning a new fine-grained concept with very little supervision, e.g., few exemplary images for a species of bird, yet our best deep learning systems need hundreds or ...
Abstract: The present paper introduces an algorithmic construction of the maximal invariant set for a PWA (piecewise affine) system. The classical analysis of this type of dynamical systems is based ...
Results that may be inaccessible to you are currently showing.
Hide inaccessible results