# MFST: Multi-Features Siamese Tracker

arXiv: https://arxiv.org/abs/2103.00810 · HTML: https://mlsanity.com/paper/2103.00810/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 1 Mar 2021.

## Builds on (most cited first, 12 of 12)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [Learning Multi-Domain Convolutional Neural Networks for Visual Tracking](https://mlsanity.com/paper/1510.07945/) (2015)
- [Distractor-aware Siamese Networks for Visual Object Tracking](https://mlsanity.com/paper/1808.06048/) (2018)
- [End-to-end representation learning for Correlation Filter based tracking](https://mlsanity.com/paper/1704.06036/) (2017)
- [Learning to Track at 100 FPS with Deep Regression Networks](https://mlsanity.com/paper/1604.01802/) (2016)
- [A Twofold Siamese Network for Real-Time Object Tracking](https://mlsanity.com/paper/1802.08817/) (2018)
- [Staple: Complementary Learners for Real-Time Tracking](https://mlsanity.com/paper/1512.01355/) (2015)
- [Large Margin Object Tracking with Circulant Feature Maps](https://mlsanity.com/paper/1703.05020/) (2017)
- [Context-aware Deep Feature Compression for High-speed Visual Tracking](https://mlsanity.com/paper/1803.10537/) (2018)
- [Robust Visual Tracking via Hierarchical Convolutional Features](https://mlsanity.com/paper/1707.03816/) (2017)
- [Multi-Branch Siamese Networks with Online Selection for Object Tracking](https://mlsanity.com/paper/1808.07349/) (2018)

## Abstract (arXiv)

Siamese trackers have recently achieved interesting results due to their balance between accuracy and speed. This success is mainly due to the fact that deep similarity networks were specifically designed to address the image similarity problem. Therefore, they are inherently more appropriate than classical CNNs for the tracking task. However, Siamese trackers rely on the last convolutional layers for similarity analysis and target search, which restricts their performance. In this paper, we argue that using a single convolutional layer as feature representation is not the optimal choice within the deep similarity framework, as multiple convolutional layers provide several abstraction levels in characterizing an object. Starting from this motivation, we present the Multi-Features Siamese Tracker (MFST), a novel tracking algorithm exploiting several hierarchical feature maps for robust deep similarity tracking. MFST proceeds by fusing hierarchical features to ensure a richer and more efficient representation. Moreover, we handle appearance variation by calibrating deep features extracted from two different CNN models. Based on this advanced feature representation, our algorithm achieves high tracking accuracy, while outperforming several state-of-the-art trackers, including standard Siamese trackers. The code and trained models are available at https://github.com/zhenxili96/MFST.