Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking

• URL: http://arxiv.org/abs/2503.06625v1
• Date: Sun, 09 Mar 2025 14:02:30 GMT
• Title: Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking
• Authors: Chaocan Xue, Bineng Zhong, Qihua Liang, Yaozong Zheng, Ning Li, Yuanliang Xue, Shuxiang Song,
• Abstract summary: Vision transformers (ViTs) have emerged as a popular backbone for visual tracking.<n>ViTs are too cumbersome to deploy for unmanned aerial vehicle (UAV) tracking.<n>We propose a similarity-guided layer adaptation approach to optimize the structure of ViTs.
• Score: 11.602484345266484
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Vision transformers (ViTs) have emerged as a popular backbone for visual tracking. However, complete ViT architectures are too cumbersome to deploy for unmanned aerial vehicle (UAV) tracking which extremely emphasizes efficiency. In this study, we discover that many layers within lightweight ViT-based trackers tend to learn relatively redundant and repetitive target representations. Based on this observation, we propose a similarity-guided layer adaptation approach to optimize the structure of ViTs. Our approach dynamically disables a large number of representation-similar layers and selectively retains only a single optimal layer among them, aiming to achieve a better accuracy-speed trade-off. By incorporating this approach into existing ViTs, we tailor previously complete ViT architectures into an efficient similarity-guided layer-adaptive framework, namely SGLATrack, for real-time UAV tracking. Extensive experiments on six tracking benchmarks verify the effectiveness of the proposed approach, and show that our SGLATrack achieves a state-of-the-art real-time speed while maintaining competitive tracking precision. Codes and models are available at https://github.com/GXNU-ZhongLab/SGLATrack.

Related papers

• 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)
• Learning Adaptive and View-Invariant Vision Transformer with Multi-Teacher Knowledge Distillation for Real-Time UAV Tracking [15.597151507814429]
  We introduce AVTrack, an adaptive framework designed to selectively activate transformer blocks for real-time UAV tracking.<n>To tackle the challenges posed by extreme changes in viewing angles, we propose view-invariant representations through mutual information (MI)<n>Building on it, we propose an improved tracker, dubbed AVTrack-MD, which introduces a novel MI-based multi-teacher knowledge distillation (MD) framework.
  arXiv  Detail & Related papers  (2024-12-28T03:57:44Z)
• 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)
• LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection [63.780355815743135]
  We present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder.
  arXiv  Detail & Related papers  (2024-06-05T17:07:24Z)
• 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)
• AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Tracking [17.133735660335343]
  We propose an Adaptive ViT Model Prediction tracker (AViTMP) to design a customised tracking method. This method bridges the single-branch network with discriminative models for the first time. We show that AViTMP achieves state-of-the-art performance, especially in terms of long-term tracking and robustness.
  arXiv  Detail & Related papers  (2023-10-30T13:48:04Z)
• PriViT: Vision Transformers for Fast Private Inference [55.36478271911595]
  Vision Transformer (ViT) architecture has emerged as the backbone of choice for state-of-the-art deep models for computer vision applications. ViTs are ill-suited for private inference using secure multi-party protocols, due to the large number of non-polynomial operations. We propose PriViT, an algorithm to selectively " Taylorize" nonlinearities in ViTs while maintaining their prediction accuracy.
  arXiv  Detail & Related papers  (2023-10-06T21:45:05Z)
• 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)
• ProContEXT: Exploring Progressive Context Transformer for Tracking [20.35886416084831]
  Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as it cannot account for changes in object appearance between frames. We revamped the framework with Progressive Context. Transformer Tracker (ProContEXT), which coherently exploits spatial and temporal contexts to predict object motion trajectories.
  arXiv  Detail & Related papers  (2022-10-27T14:47:19Z)
• Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking [59.79252390626194]
  We propose a novel solution named TransSTAM, which leverages Transformer to model both the appearance features of each object and the spatial-temporal relationships among objects. The proposed method is evaluated on multiple public benchmarks including MOT16, MOT17, and MOT20, and it achieves a clear performance improvement in both IDF1 and HOTA.
  arXiv  Detail & Related papers  (2022-05-31T01:19:18Z)
• Efficient Visual Tracking with Exemplar Transformers [98.62550635320514]
  We introduce the Exemplar Transformer, an efficient transformer for real-time visual object tracking. E.T.Track, our visual tracker that incorporates Exemplar Transformer layers, runs at 47 fps on a CPU. This is up to 8 times faster than other transformer-based models.
  arXiv  Detail & Related papers  (2021-12-17T18:57:54Z)
• TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking [74.82415271960315]
  We propose a solution named TransMOT to efficiently model the spatial and temporal interactions among objects in a video. TransMOT is not only more computationally efficient than the traditional Transformer, but it also achieves better tracking accuracy. The proposed method is evaluated on multiple benchmark datasets including MOT15, MOT16, MOT17, and MOT20.
  arXiv  Detail & Related papers  (2021-04-01T01:49:05Z)
• 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.