DeepOPG: Improving Orthopantomogram Finding Summarization with Weak Supervision

Visual Parsing with Weak Supervision

Multi-Resolution Language Grounding with Weak Supervision

Language is given meaning through its correspondence with a world representation. This correspondence can be at multiple levels of granularity or resolutions. In this paper, we introduce an approach to multi-resolution language grounding in the extremely challenging domain of professional soccer commentaries. We define and optimize a factored objective function that allows us to leverage discou...

Learning Transformation Invariant Representations with Weak Supervision

Benjamin Coors1,2, Alexandru Condurache2, Alfred Mertins3 and Andreas Geiger1,4 1Autonomous Vision Group, MPI for Intelligent Systems, Tübingen, Germany 2Robert Bosch GmbH, Leonberg, Germany 3Institute for Signal Processing, University of Lübeck, Germany 4Computer Vision and Geometry Group, ETH Zürich, Switzerland {benjamin.coors,andreas.geiger}@tue.mpg.de, [email protected], m...

Learning under Distributed Weak Supervision

The availability of training data for supervision is a frequently encountered bottleneck of medical image analysis methods. While typically established by a clinical expert rater, the increase in acquired imaging data renders traditional pixel-wise segmentations less feasible. In this paper, we examine the use of a crowdsourcing platform for the distribution of super-pixel weak annotation tasks...

Tuberculosis Case Finding and Supervision *

The control of tuberculosis has been an accepted objective in public health practice for many years. If present-day knowledge of the disease could be utilized to its fullest, the rate of decline would be accelerated appreciably. Present-day facilities are of little value unless the public will readily and willingly cooperate with the public health agency in utilizing this knowledge. Since Koch ...