Web: http://arxiv.org/abs/2104.05279

Jan. 14, 2022, 2:11 a.m. | Ahmet Iscen, André Araujo, Boqing Gong, Cordelia Schmid

cs.LG updates on arXiv.org arxiv.org

Real-world imagery is often characterized by a significant imbalance of the
number of images per class, leading to long-tailed distributions. An effective
and simple approach to long-tailed visual recognition is to learn feature
representations and a classifier separately, with instance and class-balanced
sampling, respectively. In this work, we introduce a new framework, by making
the key observation that a feature representation learned with instance
sampling is far from optimal in a long-tailed setting. Our main contribution is
a new training method, referred to as Class-Balanced Distillation (CBD), that
leverages knowledge …

arxiv cv for

Statistics and Computer Science Specialist

@ Hawk-Research | Remote

Data Scientist, Credit/Fraud Strategy

@ Fora Financial | New York City

Postdoctoral Research Associate - Biomedical Natural Language Processing and Deep Learning

@ Oak Ridge National Laboratory - Oak Ridge, TN | Oak Ridge, TN, United States

Senior Machine Learning / Computer Vision Engineer

@ Glass Imaging | Los Altos, CA

Research Scientist in Biomedical Natural Language Processing and Deep Learning

@ Oak Ridge National Laboratory | Oak Ridge, TN

W3-Professorship for Intelligent Energy Management

@ Universität Bayreuth | Bayreuth, Germany