SEATrack: Simple, Efficient, and Adaptive Multimodal Tracker

• URL: http://arxiv.org/abs/2604.12502v1
• Date: Tue, 14 Apr 2026 09:27:50 GMT
• Title: SEATrack: Simple, Efficient, and Adaptive Multimodal Tracker
• Abstract summary: We introduce SEATrack, a Simple, Efficient, and Adaptive two-stream multimodal tracker.<n> AMG-LoRA seamlessly integrates Low-Rank Adaptation (LoRA) for domain adaptation with Adaptive Mutual Guidance ( AMG) to dynamically refine and align attention maps.<n>We then depart from conventional local fusion approaches by introducing a Hierarchical Mixture of Experts (HMoE) that enables efficient global relation modeling.
• Score: 48.348918789044
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parameter-efficient fine-tuning (PEFT) in multimodal tracking reveals a concerning trend where recent performance gains are often achieved at the cost of inflated parameter budgets, which fundamentally erodes PEFT's efficiency promise. In this work, we introduce SEATrack, a Simple, Efficient, and Adaptive two-stream multimodal tracker that tackles this performance-efficiency dilemma from two complementary perspectives. We first prioritize cross-modal alignment of matching responses, an underexplored yet pivotal factor that we argue is essential for breaking the trade-off. Specifically, we observe that modality-specific biases in existing two-stream methods generate conflicting matching attention maps, thereby hindering effective joint representation learning. To mitigate this, we propose AMG-LoRA, which seamlessly integrates Low-Rank Adaptation (LoRA) for domain adaptation with Adaptive Mutual Guidance (AMG) to dynamically refine and align attention maps across modalities. We then depart from conventional local fusion approaches by introducing a Hierarchical Mixture of Experts (HMoE) that enables efficient global relation modeling, effectively balancing expressiveness and computational efficiency in cross-modal fusion. Equipped with these innovations, SEATrack advances notable progress over state-of-the-art methods in balancing performance with efficiency across RGB-T, RGB-D, and RGB-E tracking tasks. \href{https://github.com/AutoLab-SAI-SJTU/SEATrack}{\textcolor{cyan}{Code is available}}.

Related papers

• MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search [12.345218777941108]
  Fine-tuning Multimodal Large Language Models (MLLMs) with parameter-efficient methods like Low-Rank Adaptation (LoRA) is crucial for task adaptation.<n>We introduce MARS (Multimodal Adaptive Rank Search), an approach to discover optimal rank pairs that balance training dynamics while maximizing performance.<n>Our key innovation, a proposed framework of dual scaling laws, enables this search: one law models module-specific convergence time to prune the search space to candidates with aligned dynamics, while the other predicts final task performance to select the optimal pair from the pruned set.
  arXiv  Detail & Related papers  (2026-02-28T15:58:28Z)
• FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts [44.21416999726094]
  Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for foundation models.<n>MoE-based LoRA variants show promise in mitigating intra-task correlations in single-task instruction tuning.<n>FlyLoRA is an implicit MoE-based LoRA variant that introduces rank-wise expert activation in the up-projection matrix.
  arXiv  Detail & Related papers  (2025-10-09T16:17:13Z)
• RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness [28.437105789298244]
  RobustMerge is a training-free parameter-efficient merging method with complementary parameter adaptation to maintain direction robustness.<n>We establish a benchmark consisting of diverse multimodal tasks, on which we conduct experiments to certify the outstanding performance and generalizability of our method.
  arXiv  Detail & Related papers  (2025-02-24T13:52:05Z)
• CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction [77.8576094863446]
  We propose a new detextbfCoupled dutextbfAl-interactive lineatextbfR atttextbfEntion (CARE) mechanism. We first propose an asymmetrical feature decoupling strategy that asymmetrically decouples the learning process for local inductive bias and long-range dependencies. By adopting a decoupled learning way and fully exploiting complementarity across features, our method can achieve both high efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-11-25T07:56:13Z)
• Middle Fusion and Multi-Stage, Multi-Form Prompts for Robust RGB-T Tracking [1.8843687952462744]
  M3PT is a novel RGB-T prompt tracking method that leverages middle fusion and multi-modal and multi-stage visual prompts to overcome challenges. Based on the meta-framework, we utilize multiple flexible prompt strategies to adapt the pre-trained model to comprehensive exploration of uni-modal patterns.
  arXiv  Detail & Related papers  (2024-03-27T02:06:25Z)
• 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)
• Unified Single-Stage Transformer Network for Efficient RGB-T Tracking [47.88113335927079]
  We propose a single-stage Transformer RGB-T tracking network, namely USTrack, which unifies the above three stages into a single ViT (Vision Transformer) backbone. With this structure, the network can extract fusion features of the template and search region under the mutual interaction of modalities. Experiments on three popular RGB-T tracking benchmarks demonstrate that our method achieves new state-of-the-art performance while maintaining the fastest inference speed 84.2FPS.
  arXiv  Detail & Related papers  (2023-08-26T05:09:57Z)
• Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework [76.70603443624012]
  We propose a novel one-stream tracking (OSTrack) framework that unifies feature learning and relation modeling. In this way, discriminative target-oriented features can be dynamically extracted by mutual guidance. OSTrack achieves state-of-the-art performance on multiple benchmarks, in particular, it shows impressive results on the one-shot tracking benchmark GOT-10k.
  arXiv  Detail & Related papers  (2022-03-22T18:37:11Z)
• Pruning Self-attentions into Convolutional Layers in Single Path [89.55361659622305]
  Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. We propose Single-Path Vision Transformer pruning (SPViT) to efficiently and automatically compress the pre-trained ViTs. Our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously.
  arXiv  Detail & Related papers  (2021-11-23T11:35:54Z)
• Amortized Auto-Tuning: Cost-Efficient Transfer Optimization for Hyperparameter Recommendation [83.85021205445662]
  We propose an instantiation--amortized auto-tuning (AT2) to speed up tuning of machine learning models. We conduct a thorough analysis of the multi-task multi-fidelity Bayesian optimization framework, which leads to the best instantiation--amortized auto-tuning (AT2)
  arXiv  Detail & Related papers  (2021-06-17T00:01:18Z)
• Higher Performance Visual Tracking with Dual-Modal Localization [106.91097443275035]
  Visual Object Tracking (VOT) has synchronous needs for both robustness and accuracy. We propose a dual-modal framework for target localization, consisting of robust localization suppressingors via ONR and the accurate localization attending to the target center precisely via OFC.
  arXiv  Detail & Related papers  (2021-03-18T08:47:56Z)

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.