Learn to Match: Automatic Matching Network Design for Visual Tracking

• URL: http://arxiv.org/abs/2108.00803v1
• Date: Mon, 2 Aug 2021 12:09:23 GMT
• Title: Learn to Match: Automatic Matching Network Design for Visual Tracking
• Abstract summary: We introduce six novel matching operators instead of explicit similarity learning. We propose binary channel manipulation to search for the optimal combination of these operators. Our model achieves favorable gains by $67.2 rightarrow 71.4$, $52.6 rightarrow 58.3$, $70.3 rightarrow 76.0$ success on OTB100, LaSOT, and TrackingNet.
• Score: 43.476030483114094
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Siamese tracking has achieved groundbreaking performance in recent years, where the essence is the efficient matching operator cross-correlation and its variants. Besides the remarkable success, it is important to note that the heuristic matching network design relies heavily on expert experience. Moreover, we experimentally find that one sole matching operator is difficult to guarantee stable tracking in all challenging environments. Thus, in this work, we introduce six novel matching operators from the perspective of feature fusion instead of explicit similarity learning, namely Concatenation, Pointwise-Addition, Pairwise-Relation, FiLM, Simple-Transformer and Transductive-Guidance, to explore more feasibility on matching operator selection. The analyses reveal these operators' selective adaptability on different environment degradation types, which inspires us to combine them to explore complementary features. To this end, we propose binary channel manipulation (BCM) to search for the optimal combination of these operators. BCM determines to retrain or discard one operator by learning its contribution to other tracking steps. By inserting the learned matching networks to a strong baseline tracker Ocean, our model achieves favorable gains by $67.2 \rightarrow 71.4$, $52.6 \rightarrow 58.3$, $70.3 \rightarrow 76.0$ success on OTB100, LaSOT, and TrackingNet, respectively. Notably, Our tracker, dubbed AutoMatch, uses less than half of training data/time than the baseline tracker, and runs at 50 FPS using PyTorch. Code and model will be released at https://github.com/JudasDie/SOTS.

Related papers

• CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models [17.223855925754837]
  Embodied Visual Tracking (EVT) is a core dynamic task in embodied intelligence.<n>We propose CoMaTrack, a competitive game-theoretic multi-agent reinforcement learning framework.<n>We introduce CoMaTrack-Bench, the first open-source benchmark protocol and episode set for language-conditioned competitive EVT.
  arXiv  Detail & Related papers  (2026-03-24T06:35:19Z)
• ToaSt: Token Channel Selection and Structured Pruning for Efficient ViT [14.21482208417138]
  Vision Transformers (ViTs) have achieved remarkable success across various vision tasks, yet their deployment is often hindered by prohibitive computational costs.<n>We propose ToaSt, a decoupled framework applying specialized strategies to distinct ViT components.
  arXiv  Detail & Related papers  (2026-02-17T16:52:13Z)
• Temporal Correlation Meets Embedding: Towards a 2nd Generation of JDE-based Real-Time Multi-Object Tracking [52.04679257903805]
  Joint Detection and Embedding (JDE) trackers have demonstrated excellent performance in Multi-Object Tracking (MOT) tasks. Our tracker, named TCBTrack, achieves state-of-the-art performance on multiple public benchmarks.
  arXiv  Detail & Related papers  (2024-07-19T07:48:45Z)
• Multi-attention Associate Prediction Network for Visual Tracking [3.9628431811908533]
  classification-regression prediction networks have realized impressive success in several modern deep trackers. There is an inherent difference between classification and regression tasks, so they have diverse even opposite demands for feature matching. We propose a multi-attention associate prediction network (MAPNet) to tackle the above problems.
  arXiv  Detail & Related papers  (2024-03-25T03:18:58Z)
• UniNet: Unified Architecture Search with Convolution, Transformer, and MLP [39.489331136395535]
  We propose a novel unified architecture search approach for high-performance networks. First, we model the very different searchable operators in a unified form. Second, we propose context-aware downsampling modules (DSMs) to mitigate the gap between the different types of operators. Third, we integrate operators and DSMs into a unified search space and search with a Reinforcement Learning-based search algorithm.
  arXiv  Detail & Related papers  (2022-07-12T09:30:58Z)
• Learning Tracking Representations via Dual-Branch Fully Transformer Networks [82.21771581817937]
  We present a Siamese-like Dual-branch network based on solely Transformers for tracking. We extract a feature vector for each patch based on its matching results with others within an attention window. The method achieves better or comparable results as the best-performing methods.
  arXiv  Detail & Related papers  (2021-12-05T13:44:33Z)
• SwinTrack: A Simple and Strong Baseline for Transformer Tracking [81.65306568735335]
  We propose a fully attentional-based Transformer tracking algorithm, Swin-Transformer Tracker (SwinTrack) SwinTrack uses Transformer for both feature extraction and feature fusion, allowing full interactions between the target object and the search region for tracking. In our thorough experiments, SwinTrack sets a new record with 0.717 SUC on LaSOT, surpassing STARK by 4.6% while still running at 45 FPS.
  arXiv  Detail & Related papers  (2021-12-02T05:56:03Z)
• Identify Light-Curve Signals with Deep Learning Based Object Detection Algorithm. I. Transit Detection [4.282591407862616]
  We develop a novel detection algorithm based on a well proven object detection framework in the computer vision field. Our model yields about 90% precision and recall for identifying transits with signal-to-noise ratio higher than 6. The results of our algorithm match the intuition of the human visual perception and make it useful to find single-transiting candidates.
  arXiv  Detail & Related papers  (2021-08-02T07:15:13Z)
• Vision Transformers are Robust Learners [65.91359312429147]
  We study the robustness of the Vision Transformer (ViT) against common corruptions and perturbations, distribution shifts, and natural adversarial examples. We present analyses that provide both quantitative and qualitative indications to explain why ViTs are indeed more robust learners.
  arXiv  Detail & Related papers  (2021-05-17T02:39:22Z)
• Learning to Filter: Siamese Relation Network for Robust Tracking [30.997502234275206]
  We propose a novel Siamese relation network, which introduces two efficient modules, i.e. Relation Detector (RD) and Refinement Module (RM) RD performs in a meta-learning way to obtain a learning ability to filter the distractors from the background. RM aims to effectively integrate the proposed RD into the Siamese framework to generate accurate tracking result.
  arXiv  Detail & Related papers  (2021-04-02T00:53:33Z)
• Transformer Tracking [76.96796612225295]
  Correlation acts as a critical role in the tracking field, especially in popular Siamese-based trackers. This work presents a novel attention-based feature fusion network, which effectively combines the template and search region features solely using attention. Experiments show that our TransT achieves very promising results on six challenging datasets.
  arXiv  Detail & Related papers  (2021-03-29T09:06:55Z)

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.