SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking
- URL: http://arxiv.org/abs/2403.16002v2
- Date: Thu, 28 Mar 2024 03:22:52 GMT
- Title: SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking
- Authors: Xiaojun Hou, Jiazheng Xing, Yijie Qian, Yaowei Guo, Shuo Xin, Junhao Chen, Kai Tang, Mengmeng Wang, Zhengkai Jiang, Liang Liu, Yong Liu,
- Abstract summary: Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness.
Recent studies have utilized prompt tuning to transfer pre-trained RGB-based trackers to multimodal data.
We propose a novel symmetric multimodal tracking framework called SDSTrack.
- Score: 19.50096632818305
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness. Early research focused on fully fine-tuning RGB-based trackers, which was inefficient and lacked generalized representation due to the scarcity of multimodal data. Therefore, recent studies have utilized prompt tuning to transfer pre-trained RGB-based trackers to multimodal data. However, the modality gap limits pre-trained knowledge recall, and the dominance of the RGB modality persists, preventing the full utilization of information from other modalities. To address these issues, we propose a novel symmetric multimodal tracking framework called SDSTrack. We introduce lightweight adaptation for efficient fine-tuning, which directly transfers the feature extraction ability from RGB to other domains with a small number of trainable parameters and integrates multimodal features in a balanced, symmetric manner. Furthermore, we design a complementary masked patch distillation strategy to enhance the robustness of trackers in complex environments, such as extreme weather, poor imaging, and sensor failure. Extensive experiments demonstrate that SDSTrack outperforms state-of-the-art methods in various multimodal tracking scenarios, including RGB+Depth, RGB+Thermal, and RGB+Event tracking, and exhibits impressive results in extreme conditions. Our source code is available at https://github.com/hoqolo/SDSTrack.
Related papers
- Visual and Memory Dual Adapter for Multi-Modal Object Tracking [34.406308400305385]
We propose a novel visual and memory dual adapter (VMDA) to construct more robust representations for multi-modal tracking.<n>We develop a simple but effective visual adapter that adaptively transfers discriminative cues from auxiliary modality to dominant modality.<n>We also design the memory adapter inspired by the human memory mechanism, which stores global temporal cues and performs dynamic update and retrieval operations.
arXiv Detail & Related papers (2025-06-30T15:38:26Z) - Diff-MM: Exploring Pre-trained Text-to-Image Generation Model for Unified Multi-modal Object Tracking [45.341224888996514]
Multi-modal object tracking integrates auxiliary modalities such as depth, thermal infrared, event flow, and language.<n>Existing methods typically start from an RGB-based tracker and learn to understand auxiliary modalities only from training data.<n>This work proposes a unified multi-modal tracker Diff-MM by exploiting the multi-modal understanding capability of the pre-trained text-to-image generation model.
arXiv Detail & Related papers (2025-05-19T01:42:13Z) - Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos [31.910202172609313]
Existing multi-object tracking algorithms generally focus on single-modality scenes.
We propose a novel framework called HGT-Track (Heterogeneous Graph Transformer based Multi-Tiny-Object Tracking)
This paper introduces the first benchmark VT-Tiny-MOT (Visible-Thermal Tiny Multi-Object Tracking) for RGB-T fused multiple tiny object tracking.
arXiv Detail & Related papers (2024-12-14T15:17:49Z) - Bi-directional Adapter for Multi-modal Tracking [67.01179868400229]
We propose a novel multi-modal visual prompt tracking model based on a universal bi-directional adapter.
We develop a simple but effective light feature adapter to transfer modality-specific information from one modality to another.
Our model achieves superior tracking performance in comparison with both the full fine-tuning methods and the prompt learning-based methods.
arXiv Detail & Related papers (2023-12-17T05:27:31Z) - Single-Model and Any-Modality for Video Object Tracking [85.83753760853142]
We introduce Un-Track, a Unified Tracker of a single set of parameters for any modality.
To handle any modality, our method learns their common latent space through low-rank factorization and reconstruction techniques.
Our Un-Track achieves +8.1 absolute F-score gain, on the DepthTrack dataset, by introducing only +2.14 (over 21.50) GFLOPs with +6.6M (over 93M) parameters.
arXiv Detail & Related papers (2023-11-27T14:17:41Z) - Visual Prompt Multi-Modal Tracking [71.53972967568251]
Visual Prompt multi-modal Tracking (ViPT) learns the modal-relevant prompts to adapt the frozen pre-trained foundation model to various downstream multimodal tracking tasks.
ViPT outperforms the full fine-tuning paradigm on multiple downstream tracking tasks including RGB+Depth, RGB+Thermal, and RGB+Event tracking.
arXiv Detail & Related papers (2023-03-20T01:51:07Z) - Learning Dual-Fused Modality-Aware Representations for RGBD Tracking [67.14537242378988]
Compared with the traditional RGB object tracking, the addition of the depth modality can effectively solve the target and background interference.
Some existing RGBD trackers use the two modalities separately and thus some particularly useful shared information between them is ignored.
We propose a novel Dual-fused Modality-aware Tracker (termed DMTracker) which aims to learn informative and discriminative representations of the target objects for robust RGBD tracking.
arXiv Detail & Related papers (2022-11-06T07:59:07Z) - Prompting for Multi-Modal Tracking [70.0522146292258]
We propose a novel multi-modal prompt tracker (ProTrack) for multi-modal tracking.
ProTrack can transfer the multi-modal inputs to a single modality by the prompt paradigm.
Our ProTrack can achieve high-performance multi-modal tracking by only altering the inputs, even without any extra training on multi-modal data.
arXiv Detail & Related papers (2022-07-29T09:35:02Z) - Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline [80.13652104204691]
In this paper, we construct a large-scale benchmark with high diversity for visible-thermal UAV tracking (VTUAV)
We provide a coarse-to-fine attribute annotation, where frame-level attributes are provided to exploit the potential of challenge-specific trackers.
In addition, we design a new RGB-T baseline, named Hierarchical Multi-modal Fusion Tracker (HMFT), which fuses RGB-T data in various levels.
arXiv Detail & Related papers (2022-04-08T15:22:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.