# Generative Target Update for Adaptive Siamese Tracking

arXiv: https://arxiv.org/abs/2202.09938 · HTML: https://mlsanity.com/paper/2202.09938/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 21 Feb 2022.

## Builds on (most cited first, 20 of 20)

- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [Learning Discriminative Model Prediction for Tracking](https://mlsanity.com/paper/1904.07220/) (2019)
- [ATOM: Accurate Tracking by Overlap Maximization](https://mlsanity.com/paper/1811.07628/) (2018)
- [Probabilistic Regression for Visual Tracking](https://mlsanity.com/paper/2003.12565/) (2020)
- [Ocean: Object-aware Anchor-free Tracking](https://mlsanity.com/paper/2006.10721/) (2020)
- [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)
- [Deeper and Wider Siamese Networks for Real-Time Visual Tracking](https://mlsanity.com/paper/1901.01660/) (2019)
- [SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking](https://mlsanity.com/paper/1911.07241/) (2019)
- [End-to-end representation learning for Correlation Filter based tracking](https://mlsanity.com/paper/1704.06036/) (2017)
- [Learning the Model Update for Siamese Trackers](https://mlsanity.com/paper/1908.00855/) (2019)
- [VITAL: VIsual Tracking via Adversarial Learning](https://mlsanity.com/paper/1804.04273/) (2018)
- [Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking](https://mlsanity.com/paper/1812.06148/) (2018)
- [A Twofold Siamese Network for Real-Time Object Tracking](https://mlsanity.com/paper/1802.08817/) (2018)
- [Learning Dynamic Memory Networks for Object Tracking](https://mlsanity.com/paper/1803.07268/) (2018)
- [Scale Equivariance Improves Siamese Tracking](https://mlsanity.com/paper/2007.09115/) (2020)
- [Joint Representation and Truncated Inference Learning for Correlation Filter based Tracking](https://mlsanity.com/paper/1807.11071/) (2018)
- [SiamVGG: Visual Tracking using Deeper Siamese Networks](https://mlsanity.com/paper/1902.02804/) (2019)

## Abstract (arXiv)

Siamese trackers perform similarity matching with templates (i.e., target models) to recursively localize objects within a search region. Several strategies have been proposed in the literature to update a template based on the tracker output, typically extracted from the target search region in the current frame, and thereby mitigate the effects of target drift. However, this may lead to corrupted templates, limiting the potential benefits of a template update strategy. This paper proposes a model adaptation method for Siamese trackers that uses a generative model to produce a synthetic template from the object search regions of several previous frames, rather than directly using the tracker output. Since the search region encompasses the target, attention from the search region is used for robust model adaptation. In particular, our approach relies on an auto-encoder trained through adversarial learning to detect changes in a target object's appearance and predict a future target template, using a set of target templates localized from tracker outputs at previous frames. To prevent template corruption during the update, the proposed tracker also performs change detection using the generative model to suspend updates until the tracker stabilizes, and robust matching can resume through dynamic template fusion. Extensive experiments conducted on VOT-16, VOT-17, OTB-50, and OTB-100 datasets highlight the effectiveness of our method, along with the impact of its key components. Results indicate that our proposed approach can outperform state-of-art trackers, and its overall robustness allows tracking for a longer time before failure.