Surrogate Approximations for Similarity Measures

Abstract

This thesis targets the problem of surrogate approximations for similarity measures to improve their newlineperformance in various applications. We have presented surrogate approximations for popular dynamic newlinetime warping (DTW) distance, canonical correlation analysis (CCA), Intersection-over-Union (IoU), newlinePCP, and PCKh measures. For DTW and CCA, our surrogate approximations are based on their corresponding definitions. We presented a surrogate approximation using neural networks for IoU, PCP, and newlinePCKh measures. newlineFirst, we propose a linear approximation for the naïve DTW distance. We try to speed up the DTW newlinedistance computation by learning the optimal alignment from the training data. We propose a surrogate kernel approximation over CCA in our next contribution. It enables us to use CCA in the kernel newlineframework, further improving its performance. In our final contribution, we propose a surrogate approximation technique using neural networks to learn a surrogate loss function over IoU, PCP, and newlinePCKh measures. For IoU loss, we validated our method over semantic segmentation models. For PCP, newlineand PCKh loss, we validated over human pose estimation models. newline