Rethinking Convolutional Features in Correlation Filter Based Tracking
arXiv:1912.12811
Abstract
Both accuracy and efficiency are of significant importance to the task of visual object tracking. In recent years, as the surge of deep learning, Deep Convolutional NeuralNetwork (DCNN) becomes a very popular choice among the tracking community. However, due to the high computational complexity, end-to-end visual object trackers can hardly achieve an acceptable inference time and therefore can difficult to be utilized in many real-world applications. In this paper, we revisit a hierarchical deep feature-based visual tracker and found that both the performance and efficiency of the deep tracker are limited by the poor feature quality. Therefore, we propose a feature selection module to select more discriminative features for the trackers. After removing redundant features, our proposed tracker achieves significant improvements in both performance and efficiency. Finally, comparisons with state-of-the-art trackers are provided.
References in corpus (6)
- High-Speed Tracking with Kernelized Correlation Filters
- Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
- Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
- A Novel Performance Evaluation Methodology for Single-Target Trackers
- Context-aware Deep Feature Compression for High-speed Visual Tracking
- Dual Deep Network for Visual Tracking