← Search

Fedor Zhdanov

2 accepted papers

2022

Exploiting Invariance in Training Deep Neural Networks

AAAI 2022technical

Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains well with an initial learning rate 1.0, and easily generali…

2020

Rethinking Zero-Shot Video Classification: End-to-End Training for Realistic Applications

CVPR 2020poster

Trained on large datasets, deep learning (DL) can accurately classify videos into hundreds of diverse classes. However, video data is expensive to annotate. Zero-shot learning (ZSL) proposes one solution to this problem. ZSL trains a model once, and generalizes to new tasks whose classes are not pre…

Cited by 182PDFcodeScholar