What Can Style Transfer and Paintings Do For Model Robustness?

1 code implementation • CVPR 2021 • Hubert Lin, Mitchell Van Zuijlen, Sylvia C. Pont, Maarten W. A. Wijntjes, Kavita Bala

First, we investigate the role of paintings as style images for stylization-based data augmentation.

Data Augmentation Style Transfer

Insights From A Large-Scale Database of Material Depictions In Paintings

no code implementations • 24 Nov 2020 • Hubert Lin, Mitchell Van Zuijlen, Maarten W. A. Wijntjes, Sylvia C. Pont, Kavita Bala

We also find that FasterRCNN, a model which has been designed for object recognition in natural scenes, can be quickly repurposed for detection of materials in paintings.

Domain Adaptation Interactive Segmentation +1

Annotating shadows, highlights and faces: the contribution of a 'human in the loop' for digital art history

no code implementations • 10 Sep 2018 • Maarten W. A. Wijntjes

While automatic computational techniques appear to reveal novel insights in digital art history, a complementary approach seems to get less attention: that of human annotation.