Universal Correspondence Network

Christopher B. Choy, Manmohan Chandraker, JunYoung Gwak, Silvio Savarese

Neural Information Processing Systems 

We propose a convolutional spatial transformer to mimic patch normalization in traditional features like SIFT, which is shown to dramatically boost accuracy for semantic correspondences across intra-class shape variations.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found