Weakly Supervised Matching refers to a specific application of weakly supervised learning in the context of matching or aligning data. For instance, in natural language processing, weakly supervised matching could involve aligning sentences or phrases in two different languages without having a precise word-by-word alignment. It recognizes that the provided supervision is not as detailed or accurate as in fully supervised scenarios but still aims to learn meaningful correspondences between the data.


WarpNet: Weakly Supervised Matching for Single-View Reconstruction

Our WarpNet matches images of objects in fine-grained datasets without using part annotations. It aligns an object in one image with a different object in another by exploiting a fine-grained dataset to create artificial data for training a Siamese network with an unsupervised discriminative learning approach. The output of the network acts as a spatial prior that allows generalization at test time to match real images across variations in appearance, viewpoint and articulation. This allows single-view reconstruction with quality comparable to using human annotation.