# Discriminative and Robust Online Learning for Siamese Visual Tracking

arXiv: https://arxiv.org/abs/1909.02959 · HTML: https://mlsanity.com/paper/1909.02959/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2019.

## Built on by (most cited first, 10 of 10)

- [STMTrack: Template-free Visual Tracking with Space-time Memory Networks](https://mlsanity.com/paper/2104.00324/) (2021)
- [Correlation-Aware Deep Tracking](https://mlsanity.com/paper/2203.01666/) (2022)
- [Elysium: Exploring Object-level Perception in Videos via MLLM](https://mlsanity.com/paper/2403.16558/) (2024)
- [The State of Aerial Surveillance: A Survey](https://mlsanity.com/paper/2201.03080/) (2022)
- [Real-Time Visual Object Tracking via Few-Shot Learning](https://mlsanity.com/paper/2103.10130/) (2021)
- [SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking](https://mlsanity.com/paper/2602.01677/) (2026)
- [Higher Performance Visual Tracking with Dual-Modal Localization](https://mlsanity.com/paper/2103.10089/) (2021)
- [Spatio-Temporal Matching for Siamese Visual Tracking](https://mlsanity.com/paper/2105.02408/) (2021)
- [TAPL: Dynamic Part-based Visual Tracking via Attention-guided Part Localization](https://mlsanity.com/paper/2110.13027/) (2021)
- [Dynamic Attention Mechanism in Spatiotemporal Memory Networks for Object Tracking](https://mlsanity.com/paper/2503.16768/) (2025)

## Abstract (arXiv)

The problem of visual object tracking has traditionally been handled by variant tracking paradigms, either learning a model of the object's appearance exclusively online or matching the object with the target in an offline-trained embedding space. Despite the recent success, each method agonizes over its intrinsic constraint. The online-only approaches suffer from a lack of generalization of the model they learn thus are inferior in target regression, while the offline-only approaches (e.g., convolutional siamese trackers) lack the target-specific context information thus are not discriminative enough to handle distractors, and robust enough to deformation. Therefore, we propose an online module with an attention mechanism for offline siamese networks to extract target-specific features under L2 error. We further propose a filter update strategy adaptive to treacherous background noises for discriminative learning, and a template update strategy to handle large target deformations for robust learning. Effectiveness can be validated in the consistent improvement over three siamese baselines: SiamFC, SiamRPN++, and SiamMask. Beyond that, our model based on SiamRPN++ obtains the best results over six popular tracking benchmarks and can operate beyond real-time.