Ivan Skorokhodov, Mohamed Elhoseiny

Research output: Contribution to conferencePaperpeer-review

18 Scopus citations


Normalization techniques have proved to be a crucial ingredient of successful training in a traditional supervised learning regime. However, in the zero-shot learning (ZSL) world, these ideas have received only marginal attention. This work studies normalization in ZSL scenario from both theoretical and practical perspectives. First, we give a theoretical explanation to two popular tricks used in zero-shot learning: normalize+scale and attributes normalization and show that they help training by preserving variance during a forward pass. Next, we demonstrate that they are insufficient to normalize a deep ZSL model and propose Class Normalization (CN): a normalization scheme, which alleviates this issue both provably and in practice. Third, we show that ZSL models typically have more irregular loss surface compared to traditional classifiers and that the proposed method partially remedies this problem. Then, we test our approach on 4 standard ZSL datasets and outperform sophisticated modern SotA with a simple MLP optimized without any bells and whistles and having ≈50 times faster training speed. Finally, we generalize ZSL to a broader problem - continual ZSL, and introduce some principled metrics and rigorous baselines for this new setup. The source code is available at

Original languageEnglish (US)
StatePublished - 2021
Event9th International Conference on Learning Representations, ICLR 2021 - Virtual, Online
Duration: May 3 2021May 7 2021


Conference9th International Conference on Learning Representations, ICLR 2021
CityVirtual, Online

Bibliographical note

Publisher Copyright:
© 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science Applications
  • Education
  • Linguistics and Language


Dive into the research topics of 'CLASS NORMALIZATION FOR (CONTINUAL)? GENERALIZED ZERO-SHOT LEARNING'. Together they form a unique fingerprint.

Cite this