Online Learning on Non-Stationary Data Streams for Image Recognition using Deep Embeddings
Valerie Vaquet, Fabian Hinder, Jonas Vaquet, Johannes Brinkrolf, Barbara Hammer · 2021 IEEE Symposium Series on Computational Intelligence (SSCI) · 2021
Deep neural networks offer state-of-the-art technologies for highly nonlinear domains such as image processing; yet their initial training requires large amounts of data, such that they are not directly suited for online learning scenarios for streaming data where class distributions or class labels may change over time. In this contribution, we investigate the suitability of a combination of recent online learning technologies, which have been proposed for learning with streaming data and concept drift in simpler settings, and deep representations of image data as provided by deep networks trained in batch mode, to offer flexible learning technologies for streaming data from the image domain.