Web: http://arxiv.org/abs/2111.00131

Jan. 27, 2022, 2:11 a.m. | Akira Sakai, Taro Sunagawa, Spandan Madan, Kanata Suzuki, Takashi Katoh, Hiromichi Kobashi, Hanspeter Pfister, Pawan Sinha, Xavier Boix, Tomotake Sasa

cs.LG updates on arXiv.org arxiv.org

The training data distribution is often biased towards objects in certain
orientations and illumination conditions. While humans have a remarkable
capability of recognizing objects in out-of-distribution (OoD) orientations and
illuminations, Deep Neural Networks (DNNs) severely suffer in this case, even
when large amounts of training examples are available. In this paper, we
investigate three different approaches to improve DNNs in recognizing objects
in OoD orientations and illuminations. Namely, these are (i) training much
longer after convergence of the in-distribution (InD) …

arxiv cv distribution

More from arxiv.org / cs.LG updates on arXiv.org

Data Analytics and Technical support Lead

@ Coupa Software, Inc. | Bogota, Colombia

Data Science Manager

@ Vectra | San Jose, CA

Data Analyst Sr

@ Capco | Brazil - Sao Paulo

Data Scientist (NLP)

@ Builder.ai | London, England, United Kingdom - Remote

Senior Data Analyst

@ BuildZoom | Scottsdale, AZ/ San Francisco, CA/ Remote

Senior Research Scientist, Speech Recognition

@ SoundHound Inc. | Toronto, Canada