MFST: Multi-Features Siamese Tracker

by   Zhenxi Li, et al.

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



page 3


Multiple Convolutional Features in Siamese Networks for Object Tracking

Siamese trackers demonstrated high performance in object tracking due to...

Siam-ReID: Confuser Aware Siamese Tracker with Re-identification Feature

Siamese deep-network trackers have received significant attention in rec...

Joint Representation and Truncated Inference Learning for Correlation Filter based Tracking

Correlation filter (CF) based trackers generally include two modules, i....

A Strong Feature Representation for Siamese Network Tracker

Object tracking has important application in assistive technologies for ...

HiFT: Hierarchical Feature Transformer for Aerial Tracking

Most existing Siamese-based tracking methods execute the classification ...

FEAR: Fast, Efficient, Accurate and Robust Visual Tracker

We present FEAR, a novel, fast, efficient, accurate, and robust Siamese ...

Hard Negative Samples Emphasis Tracker without Anchors

Trackers based on Siamese network have shown tremendous success, because...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.