Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking

• URL: http://arxiv.org/abs/2412.20002v3
• Date: Fri, 15 Aug 2025 05:08:16 GMT
• Title: Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking
• Abstract summary: Transformer-based models have improved visual tracking, but most still cannot run in real time on resource devices.<n>We propose AVTrack, an adaptive tracking framework that adaptively activates transformer blocks through an Activation Module (AM)<n>To address extreme viewpoint variations, we propose to learn view-in representations via mutual information (MI)<n>In addition, we propose AVTrack-MD, an enhanced tracker incorporating a novel MI-based multi-teacher knowledge framework.
• Score: 15.597151507814429
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformer-based models have improved visual tracking, but most still cannot run in real time on resource-limited devices, especially for unmanned aerial vehicle (UAV) tracking. To achieve a better balance between performance and efficiency, we propose AVTrack, an adaptive computation tracking framework that adaptively activates transformer blocks through an Activation Module (AM), which dynamically optimizes the ViT architecture by selectively engaging relevant components. To address extreme viewpoint variations, we propose to learn view-invariant representations via mutual information (MI) maximization. In addition, we propose AVTrack-MD, an enhanced tracker incorporating a novel MI maximization-based multi-teacher knowledge distillation framework. Leveraging multiple off-the-shelf AVTrack models as teachers, we maximize the MI between their aggregated softened features and the corresponding softened feature of the student model, improving the generalization and performance of the student, especially under noisy conditions. Extensive experiments show that AVTrack-MD achieves performance comparable to AVTrack's performance while reducing model complexity and boosting average tracking speed by over 17\%. Codes is available at: https://github.com/wuyou3474/AVTrack.

Related papers

• UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Models [14.433739259355406]
  Embodied visual tracking is crucial for Unmanned Aerial Vehicles (UAVs) executing complex real-world tasks.<n>To benchmark multimodal tracking in such environments, we construct a large-scale dataset encompassing over 890K frames, 176 tasks, and 85 diverse objects.<n>We propose an improved VLA tracking model, UAV-Track VLA, built upon the $_0.5$ architecture.
  arXiv  Detail & Related papers  (2026-04-02T16:33:38Z)
• UniTrack: Differentiable Graph Representation Learning for Multi-Object Tracking [5.241700353040585]
  UniTrack is a plug-and-play graph-theoretic loss function designed to enhance multi-object tracking (MOT)<n>We show up to 53% reduction in identity switches and 12% IDF1 improvements across challenging benchmarks, with peak performance gains 9.7% MOTA on SportsMOT.
  arXiv  Detail & Related papers  (2026-02-04T20:44:16Z)
• Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos [58.156141601478794]
  Multi-object tracking (UAVT) aims to track multiple objects while maintaining consistent identities across frames of a given video.<n>Existing methods typically model motion cues and appearance separately, overlooking their interplay and resulting in suboptimal tracking performance.<n>We propose AMOT, which exploits appearance and motion cues through two key components: an Appearance-Motion Consistency (AMC) matrix and a Motion-aware Track Continuation (MTC) module.
  arXiv  Detail & Related papers  (2025-08-03T12:06:47Z)
• DARTer: Dynamic Adaptive Representation Tracker for Nighttime UAV Tracking [1.515687944002438]
  Nighttime UAV tracking presents significant challenges due to extreme illumination variations and viewpoint changes.<n>textbfDARTer (textbfDynamic textbfAdaptive textbfRepresentation textbfTracker) is an end-to-end tracking framework designed for nighttime UAV scenarios.
  arXiv  Detail & Related papers  (2025-05-01T05:24:14Z)
• DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs [124.52164183968145]
  We present DyMU, an efficient, training-free framework that reduces the computational burden of vision-language models (VLMs)<n>Our approach comprises two key components. First, Dynamic Token Merging (DToMe) reduces the number of visual token embeddings by merging similar tokens based on image complexity.<n>Second, Virtual Token Unmerging (VTU) simulates the expected token sequence for large language models (LLMs) by efficiently reconstructing the attention dynamics of a full sequence.
  arXiv  Detail & Related papers  (2025-04-23T18:38:18Z)
• Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking [11.146155422858824]
  Single-stream architectures using Vision Transformer (ViT) backbones show great potential for real-time UAV tracking. We propose to learn Occlusion-Robust Representations (ORR) based on ViTs for UAV tracking. We also propose an Adaptive Feature-Based Knowledge Distillation (AFKD) method to create a more compact tracker.
  arXiv  Detail & Related papers  (2025-04-12T14:06:50Z)
• Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking [11.602484345266484]
  Vision transformers (ViTs) have emerged as a popular backbone for visual tracking. ViTs are too cumbersome to deploy for unmanned aerial vehicle (UAV) tracking. We propose a similarity-guided layer adaptation approach to optimize the structure of ViTs.
  arXiv  Detail & Related papers  (2025-03-09T14:02:30Z)
• Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning [59.001091197106085]
  Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and in tegrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning. We propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained Vision Transformer into an efficient multi-task learner.
  arXiv  Detail & Related papers  (2025-01-12T17:41:23Z)
• A Cross-Scene Benchmark for Open-World Drone Active Tracking [54.235808061746525]
  Drone Visual Active Tracking aims to autonomously follow a target object by controlling the motion system based on visual observations.<n>We propose a unified cross-scene cross-domain benchmark for open-world drone active tracking called DAT.<n>We also propose a reinforcement learning-based drone tracking method called R-VAT.
  arXiv  Detail & Related papers  (2024-12-01T09:37:46Z)
• T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design [79.7289790249621]
  Our proposed method, T2V-Turbo-v2, introduces a significant advancement by integrating various supervision signals. We highlight the crucial importance of tailoring datasets to specific learning objectives. We demonstrate the potential of this approach by extracting motion guidance from the training datasets and incorporating it into the ODE solver.
  arXiv  Detail & Related papers  (2024-10-08T04:30:06Z)
• Learning Motion Blur Robust Vision Transformers with Dynamic Early Exit for Real-Time UAV Tracking [14.382072224997074]
  Single-stream architectures utilizing pre-trained ViT backbones offer improved performance, efficiency, and robustness. We boost the efficiency of this framework by tailoring it into an adaptive framework that dynamically exits Transformer blocks for real-time UAV tracking. We also improve the effectiveness of ViTs in handling motion blur, a common issue in UAV tracking caused by the fast movements of either the UAV, the tracked objects, or both.
  arXiv  Detail & Related papers  (2024-07-07T14:10:04Z)
• Exploring Dynamic Transformer for Efficient Object Tracking [58.120191254379854]
  We propose DyTrack, a dynamic transformer framework for efficient tracking. DyTrack automatically learns to configure proper reasoning routes for various inputs, gaining better utilization of the available computational budget. Experiments on multiple benchmarks demonstrate that DyTrack achieves promising speed-precision trade-offs with only a single model.
  arXiv  Detail & Related papers  (2024-03-26T12:31:58Z)
• Tiny Multi-Agent DRL for Twins Migration in UAV Metaverses: A Multi-Leader Multi-Follower Stackelberg Game Approach [57.15309977293297]
  The synergy between Unmanned Aerial Vehicles (UAVs) and metaverses is giving rise to an emerging paradigm named UAV metaverses. We propose a tiny machine learning-based Stackelberg game framework based on pruning techniques for efficient UT migration in UAV metaverses.
  arXiv  Detail & Related papers  (2024-01-18T02:14:13Z)
• VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness [56.87603097348203]
  VeCAF uses labels and natural language annotations to perform parametric data selection for PVM finetuning. VeCAF incorporates the finetuning objective to select significant data points that effectively guide the PVM towards faster convergence. On ImageNet, VeCAF uses up to 3.3x less training batches to reach the target performance compared to full finetuning.
  arXiv  Detail & Related papers  (2024-01-15T17:28:37Z)
• Mutual-Learning Knowledge Distillation for Nighttime UAV Tracking [10.170363860678663]
  Nighttime unmanned aerial vehicle (UAV) tracking has been facilitated with indispensable plug-and-play low-light enhancers. This work proposes a novel mutual-learning knowledge distillation framework for nighttime UAV tracking, i.e., MLKD.
  arXiv  Detail & Related papers  (2023-12-13T04:06:18Z)
• Divert More Attention to Vision-Language Object Tracking [87.31882921111048]
  We argue that the lack of large-scale vision-language annotated videos and ineffective vision-language interaction learning motivate us to design more effective vision-language representation for tracking. Particularly, in this paper, we first propose a general attribute annotation strategy to decorate videos in six popular tracking benchmarks, which contributes a large-scale vision-language tracking database with more than 23,000 videos. We then introduce a novel framework to improve tracking by learning a unified-adaptive VL representation, where the cores are the proposed asymmetric architecture search and modality mixer (ModaMixer)
  arXiv  Detail & Related papers  (2023-07-19T15:22:06Z)
• SGDViT: Saliency-Guided Dynamic Vision Transformer for UAV Tracking [12.447854608181833]
  This work presents a novel saliency-guided dynamic vision Transformer (SGDViT) for UAV tracking. The proposed method designs a new task-specific object saliency mining network to refine the cross-correlation operation. A lightweight saliency filtering Transformer further refines saliency information and increases the focus on appearance information.
  arXiv  Detail & Related papers  (2023-03-08T05:01:00Z)
• AttTrack: Online Deep Attention Transfer for Multi-object Tracking [4.5116674432168615]
  Multi-object tracking (MOT) is a vital component of intelligent video analytics applications such as surveillance and autonomous driving. In this paper, we aim to accelerate MOT by transferring the knowledge from high-level features of a complex network (teacher) to a lightweight network (student) at both training and inference times. The proposed AttTrack framework has three key components: 1) cross-model feature learning to align intermediate representations from the teacher and student models, 2) interleaving the execution of the two models at inference time, and 3) incorporating the updated predictions from the teacher model as prior knowledge to assist the student model
  arXiv  Detail & Related papers  (2022-10-16T22:15:31Z)
• Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching [67.02962970820505]
  We introduce "tracking-by-detection" into Video Object (VOS) We propose a new temporal aggregation network and a novel dynamic time-evolving template matching mechanism to achieve significantly improved performance. We achieve new state-of-the-art performance on the DAVIS benchmark without complicated bells and whistles in both speed and accuracy, with a speed of 0.14 second per frame and J&F measure of 75.9% respectively.
  arXiv  Detail & Related papers  (2020-07-11T05:44:16Z)

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.