RanDumb: a simple approach that questions the efficacy of continual representation learning

<p>We propose RanDumb to examine the efficacy of continual representation learning. RanDumb embeds raw pixels using a fixed random transform which approximates an RBF-Kernel, initialized before seeing any data, and learns a simple linear classifier on top. We present a surprising and consisten...

Szczegółowa specyfikacja

Opis bibliograficzny
Główni autorzy: Prabhu, A, Sinha, S, Kumaraguru, P, Torr, PHS, Sener, O, Dokania, PK
Format: Conference item
Język:English
Wydane: Neural Information Processing Systems 2025