When: April 5, 2017, 12:30 PM
Location: 3rd Floor Orchard View Room , Discovery Building
Contact: 608-316-4401, email@example.com
Image colorization and its role in visual learning
I will present our recent and ongoing work on fully automatic image colorization. Our approach exploits both low-level and semantic representations during colorization. As many scene elements naturally appear according to multimodal color distributions, we train our model to predict per-pixel color histograms. Our system achieves state-of-the-art results under a variety of metrics. Moreover, it provides a vehicle to explore the role the colorization task can play as a proxy for visual understanding, providing a self-supervision mechanism for learning representations. I will describe the ability of our self-supervised network in several contexts, such as classification and semantic segmentation. On VOC segmentation and classification tasks, we present results that are state-of-the-art among methods not using massive supervised pre-training.
Joint work with Gustav Larsson and Michael Maire.
More information about Greg Shakhnarovich.
SILO is a lecture series with speakers from the UW faculty, graduate students or invited researchers that discuss mathematical related topics. The seminars are organized by WID’s Optimization research group and sponsored by generous support of the Advance Technology Group of the 3M Company and the Analytics Group of Northwestern Mutual.
SILO’s purpose is to provide a forum that helps connect and recruit mathematically-minded graduate students. SILO is a lunch-and-listen format, where speakers present interesting math topics while the audience eats lunch.