A Twofold Siamese Network For Real-time Object Tracking

Abstract

Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Siamese network, named SA-Siam, for real-time object tracking. SA-Siam is composed of a semantic branch and an appearance branch. Each branch is a similarity-learning Siamese network. An important design choice in SA-Siam is to separately train the two branches to keep the heterogeneity of the two types of features. In addition, we propose a channel attention mechanism for the semantic branch. Channel-wise weights are computed according to the channel activations around the target position. While the inherited architecture from SiamFC \cite\{SiamFC\} allows our tracker to operate beyond real-time, the twofold design and the attention mechanism significantly improve the tracking performance. The proposed SA-Siam outperforms all other real-time trackers by a large margin on OTB-2013/50/100 benchmarks.

Stats

• citations540
• S2 citations—
• github stars0
• HF likes0
• heat score20.50
• arxiv keyhe2018a

Related papers

• Multiple Convolutional Features In Siamese Networks For Object Tracking (2021)7.73
• MFST: Multi-features Siamese Tracker (2021)0.95
• Smiletrack: Similarity Learning For Occlusion-aware Multiple Object Tracking (2022)17.36
• Deep Similarity Metric Learning For Real-time Pedestrian Tracking (2018)0.00
• Semi-supervised Learning Using Siamese Networks (2021)7.50
• Retrieval Of Family Members Using Siamese Neural Network (2020)7.81
• An Experimental Evaluation Of Siamese Neural Networks For Robot Localization Using Omnidirectional Imaging In Indoor Environments (2024)6.34
• Qdtrack: Quasi-dense Similarity Learning For Appearance-only Multiple Object Tracking (2022)15.75