Deformable Object Tracking with Gated Fusion

TL;DR

This paper introduces a deformable convolution layer and a gated fusion scheme to improve object tracking by better handling appearance variations caused by pose changes and environmental factors.

Contribution

It proposes a novel deformable convolution layer combined with gated fusion to enhance target appearance modeling in tracking-by-detection frameworks.

Findings

Outperforms state-of-the-art trackers on standard benchmarks.

Effectively captures appearance variations due to pose and environmental changes.

Enriches feature representations for more accurate object discrimination.

Abstract

The tracking-by-detection framework receives growing attentions through the integration with the Convolutional Neural Networks (CNNs). Existing tracking-by-detection based methods, however, fail to track objects with severe appearance variations. This is because the traditional convolutional operation is performed on fixed grids, and thus may not be able to find the correct response while the object is changing pose or under varying environmental conditions. In this paper, we propose a deformable convolution layer to enrich the target appearance representations in the tracking-by-detection framework. We aim to capture the target appearance variations via deformable convolution, which adaptively enhances its original features. In addition, we also propose a gated fusion scheme to control how the variations captured by the deformable convolution affect the original appearance. The enriched feature representation through deformable convolution facilitates the discrimination of the CNN classifier on the target object and background. Extensive experiments on the standard benchmarks show that the proposed tracker performs favorably against state-of-the-art methods.