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

## TL;DR

This paper introduces a novel end-to-end deep learning approach that integrates correlation filters as differentiable layers, enabling the learning of task-specific deep features for fast and accurate object tracking.

## Contribution

It is the first to interpret the correlation filter as a differentiable layer within a neural network, allowing joint learning of features and tracking.

## Key findings

- Achieves state-of-the-art tracking performance.
- Enables lightweight models to operate at high framerates.
- Demonstrates improved accuracy over traditional methods.

## Abstract

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.