End-to-end representation learning for Correlation Filter based tracking

The Correlation Filter is an algorithm that trains a linear template to discriminate between images and their translations. It is well suited to object tracking because its formulation in the Fourier domain provides a fast solution, enabling the detector to be re-trained once per frame... Previous works that use the Correlation Filter, however, have adopted features that were either manually designed or trained for a different task. This work is the first to overcome this limitation by interpreting the Correlation Filter learner, which has a closed-form solution, as a differentiable layer in a deep neural network. This enables learning deep features that are tightly coupled to the Correlation Filter. Experiments illustrate that our method has the important practical benefit of allowing lightweight architectures to achieve state-of-the-art performance at high framerates. read more

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Visual Object Tracking OTB-2013 CFNet AUC 0.611 # 6
Visual Object Tracking OTB-2015 CFNet AUC 0.568 # 9
Visual Object Tracking OTB-50 CFNet AUC 0.530 # 3

Methods


No methods listed for this paper. Add relevant methods here