Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences

Understand

We propose Probabilistic Warp Consistency, a weakly-supervised learning objective for semantic matching.

• Our approach directly supervises the dense matching scores predicted by the network, encoded as a conditional probability distribution.
• We first construct an image triplet by applying a known warp to one of the images in a pair depicting different instances of the same object class.
• Our probabilistic learning objectives are then derived using the constraints arising from the resulting image triplet.