GRSiamFC: Group Residual Convolutional Siamese Networks for Object Tracking
- 14 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 614-619
Abstract
Visual tracking has seen considerable success with fully convolutional Siamese networks (SiamFC). However, the features extracted by SiamFC are redundant in practical applications. Most of the feature channels are ineffective or even serve as noise, which adversely affects tracking performance. The convolutional kernels tend to converge during the training phase of SiamFC, thereby the output features are typically redundant or irrelevant. In this paper, we propose a group residual convolutional Siamese network (GRSiamFC) to address this problem. Specifically, GRSiamFC divides the convolutional layers used for feature extraction into groups and trains each group in turn. Then the residuals between the output of previous groups and the true labels are used as losses to guide the current group to learn the residuals that were not fitted by the previous group, thereby improving the discriminative ability of the model. Extensive experiments on OTB50, OTB100, UAV123, and UAV20L show that the proposed GRSiamFC significantly improves the performance of SiamFC while keeping the complexity unchanged.Keywords
Funding Information
- Natural Science Foundation of China (61972307)
This publication has 25 references indexed in Scilit:
- Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking2018
- ECO: Efficient Convolution Operators for Tracking2017
- Discriminative Correlation Filter with Channel and Spatial Reliability2017
- Siamese Instance Search for Tracking2016
- Fully-Convolutional Siamese Networks for Object Tracking2016
- A Benchmark and Simulator for UAV Tracking2016
- Learning to Track at 100 FPS with Deep Regression Networks2016
- Deep Residual Learning for Image Recognition2016
- Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking2016
- Staple: Complementary Learners for Real-Time Tracking2016