Feature Translation for Exemplar-Free Class-Incremental Learning
Transfer-learning-based method addressing exemplar-free class-incremental learning

Main Characteristic
FeTrIL combines a fixed feature extractor and a pseudo-features generator to improve the stability-plasticity balance. The generator uses a simple yet effective geometric translation of new class features to create representations of past classes made of pseudo-features. The translation of features only requires the storage of the centroid representations of past classes to produce their pseudo-features. Actual features of new classes and pseudo-features of past classes are fed into a linear classifier, which is trained incrementally to discriminate between all classes.
Technical Categories
Computer vision
Last updated
28.05.2024 - 13:23