Möbius signifies approaches that go beyond linear transformations and incorporate deeper, more complex interactions or transformations inspired by the Möbius strip’s unique properties in mathematics. These concepts draw inspiration from the Möbius strip in mathematics, particularly in the way they handle transformations or interactions in complex data spaces.

Posts

Learning random-walk label propagation for weakly-supervised semantic segmentation

/in /by

Large-scale training for semantic segmentation is challenging due to the expense of obtaining training data for this task relative to other vision tasks. We propose a novel training approach to address this difficulty. Given cheaply-obtained sparse image labelings, we propagate the sparse labels to produce guessed dense labelings. A standard CNN-based segmentation network is trained to mimic these labelings. The label-propagation process is defined via random-walk hitting probabilities, which leads to a differentiable parameterization with uncertainty estimates that are incorporated into our loss. We show that by learning the label-propagator jointly with the segmentation predictor, we are able to effectively learn semantic edges given no direct edge supervision. Experiments also show that training a segmentation network in this way outperforms the naive approach.

Read more