AutoScaler: Scale-Attention Networks for Visual Correspondence
british machine vision conference, 2017.
Finding visual correspondence between local features is key to many computer vision problems. While defining features with larger contextual scales usually implies greater discriminativeness, it could also lead to less spatial accuracy of the features. We propose AutoScaler, a scale-attention network to explicitly optimize this trade-off ...More
Full Text (Upload PDF)
PPT (Upload PPT)