[ContinualAI Reading Group] Bookworm Continual Learning: beyond zero-shot learning and continual learning

[02-10-2020] This Friday 5pm CEST Luis Herranz will present the paper:

Title : “Bookworm continual learning: beyond zero-shot learning and continual learning”

Abstract : We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually. Thus BCL generalizes both continual learning (CL) and zero-shot learning (ZSL). We also propose the bidirectional imagination (BImag) framework to address BCL where features of both past and future classes are generated. We observe that conditioning the feature generator on attributes can actually harm the continual learning ability, and propose two variants (joint class-attribute conditioning and asymmetric generation) to alleviate this problem.

The event will be moderated by : Vincenzo Lomonaco

:round_pushpin: YouTube Recoding : https://youtu.be/KeeX445siGg
:round_pushpin: Eventbrite event (to save it in you calendar and get reminders): https://www.eventbrite.com/e/bookworm-continual-learning-beyond-zero-shot-learning-and-cl-tickets-123141875665
:round_pushpin: Slides : http://lherranz.org/local/talks/bcl_continualAI2020.pdf