# D3S -- A Discriminative Single Shot Segmentation Tracker

arXiv: https://arxiv.org/abs/1911.08862 · HTML: https://mlsanity.com/paper/1911.08862/

## Key facts

- Cited by 69 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2019.

## Built on by (most cited first, 30 of 69)

- [Transformer Tracking](https://mlsanity.com/paper/2103.15436/) (2021)
- [Learning Spatio-Temporal Transformer for Visual Tracking](https://mlsanity.com/paper/2103.17154/) (2021)
- [Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework](https://mlsanity.com/paper/2203.11991/) (2022)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking](https://mlsanity.com/paper/2103.11681/) (2021)
- [Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark](https://mlsanity.com/paper/2103.16746/) (2021)
- [Towards Grand Unification of Object Tracking](https://mlsanity.com/paper/2207.07078/) (2022)
- [STMTrack: Template-free Visual Tracking with Space-time Memory Networks](https://mlsanity.com/paper/2104.00324/) (2021)
- [Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline](https://mlsanity.com/paper/2204.04120/) (2022)
- [Transformer Tracking with Cyclic Shifting Window Attention](https://mlsanity.com/paper/2205.03806/) (2022)
- [TCTrack: Temporal Contexts for Aerial Tracking](https://mlsanity.com/paper/2203.01885/) (2022)
- [Learn to Match: Automatic Matching Network Design for Visual Tracking](https://mlsanity.com/paper/2108.00803/) (2021)
- [DepthTrack : Unveiling the Power of RGBD Tracking](https://mlsanity.com/paper/2108.13962/) (2021)
- [Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2108.04728/) (2021)
- [Do Different Tracking Tasks Require Different Appearance Models?](https://mlsanity.com/paper/2107.02156/) (2021)
- [Joint Inductive and Transductive Learning for Video Object Segmentation](https://mlsanity.com/paper/2108.03679/) (2021)
- [MixFormerV2: Efficient Fully Transformer Tracking](https://mlsanity.com/paper/2305.15896/) (2023)
- [Unsupervised Domain Adaptation for Nighttime Aerial Tracking](https://mlsanity.com/paper/2203.10541/) (2022)
- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking](https://mlsanity.com/paper/2208.09787/) (2022)
- [Robust Visual Tracking by Segmentation](https://mlsanity.com/paper/2203.11191/) (2022)
- [Unified Transformer Tracker for Object Tracking](https://mlsanity.com/paper/2203.15175/) (2022)
- [Towards Universal Modal Tracking with Online Dense Temporal Token Learning](https://mlsanity.com/paper/2507.20177/) (2025)
- [Towards Real-World Visual Tracking with Temporal Contexts](https://mlsanity.com/paper/2308.10330/) (2023)
- [Visual Object Tracking in First Person Vision](https://mlsanity.com/paper/2209.13502/) (2022)
- [Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking](https://mlsanity.com/paper/2507.21606/) (2025)
- [DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks](https://mlsanity.com/paper/2304.00571/) (2023)
- [Is First Person Vision Challenging for Object Tracking?](https://mlsanity.com/paper/2108.13665/) (2021)
- [Active Learning for Deep Visual Tracking](https://mlsanity.com/paper/2110.13259/) (2021)
- [OmniTracker: Unifying Object Tracking by Tracking-with-Detection](https://mlsanity.com/paper/2303.12079/) (2023)

## Abstract (arXiv)

Template-based discriminative trackers are currently the dominant tracking paradigm due to their robustness, but are restricted to bounding box tracking and a limited range of transformation models, which reduces their localization accuracy. We propose a discriminative single-shot segmentation tracker - D3S, which narrows the gap between visual object tracking and video object segmentation. A single-shot network applies two target models with complementary geometric properties, one invariant to a broad range of transformations, including non-rigid deformations, the other assuming a rigid object to simultaneously achieve high robustness and online target segmentation. Without per-dataset finetuning and trained only for segmentation as the primary output, D3S outperforms all trackers on VOT2016, VOT2018 and GOT-10k benchmarks and performs close to the state-of-the-art trackers on the TrackingNet. D3S outperforms the leading segmentation tracker SiamMask on video object segmentation benchmark and performs on par with top video object segmentation algorithms, while running an order of magnitude faster, close to real-time.