Generative Target Update for Adaptive Siamese Tracking

• URL: http://arxiv.org/abs/2202.09938v1
• Date: Mon, 21 Feb 2022 00:22:49 GMT
• Title: Generative Target Update for Adaptive Siamese Tracking
• Authors: Madhu Kiran, Le Thanh Nguyen-Meidine, Rajat Sahay, Rafael Menelau Oliveira E Cruz, Louis-Antoine Blais-Morin and Eric Granger
• Abstract summary: Siamese trackers perform similarity matching with templates (i.e., target models) to localize objects within a search region. Several strategies have been proposed in the literature to update a template based on the tracker output, typically extracted from the target search region in the current frame. This paper proposes a model adaptation method for Siamese trackers that uses a generative model to produce a synthetic template from the object search regions of several previous frames.
• Score: 7.662745552551165
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Siamese trackers perform similarity matching with templates (i.e., target models) to recursively localize objects within a search region. Several strategies have been proposed in the literature to update a template based on the tracker output, typically extracted from the target search region in the current frame, and thereby mitigate the effects of target drift. However, this may lead to corrupted templates, limiting the potential benefits of a template update strategy. This paper proposes a model adaptation method for Siamese trackers that uses a generative model to produce a synthetic template from the object search regions of several previous frames, rather than directly using the tracker output. Since the search region encompasses the target, attention from the search region is used for robust model adaptation. In particular, our approach relies on an auto-encoder trained through adversarial learning to detect changes in a target object's appearance and predict a future target template, using a set of target templates localized from tracker outputs at previous frames. To prevent template corruption during the update, the proposed tracker also performs change detection using the generative model to suspend updates until the tracker stabilizes, and robust matching can resume through dynamic template fusion. Extensive experiments conducted on VOT-16, VOT-17, OTB-50, and OTB-100 datasets highlight the effectiveness of our method, along with the impact of its key components. Results indicate that our proposed approach can outperform state-of-art trackers, and its overall robustness allows tracking for a longer time before failure.

Related papers

• Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture [58.60915132222421]
  We introduce an approach that is both general and parameter-efficient for face forgery detection. We design a forgery-style mixture formulation that augments the diversity of forgery source domains. We show that the designed model achieves state-of-the-art generalizability with significantly reduced trainable parameters.
  arXiv  Detail & Related papers  (2024-08-23T01:53:36Z)
• Ada-Tracker: Soft Tissue Tracking via Inter-Frame and Adaptive-Template Matching [37.968954191944576]
  We exploit optical flow to naturally capture the pixel-wise tissue deformations and adaptively correct the tracked template. Ada-Tracker achieves superior accuracy and performs more robustly against prior works.
  arXiv  Detail & Related papers  (2024-03-11T07:42:40Z)
• BackTrack: Robust template update via Backward Tracking of candidate template [30.38433988212259]
  BackTrack is a generic template update scheme and is applicable to any template-based trackers. BackTrack is a robust and reliable method to quantify the confidence of the candidate template by backward tracking it on the past frames.
  arXiv  Detail & Related papers  (2023-08-21T10:00:59Z)
• Robust Object Modeling for Visual Tracking [36.05869157990915]
  We propose a robust object modeling framework for visual tracking (ROMTrack) ROMTrack simultaneously models the inherent template and the hybrid template features. Variation tokens are adaptable to object deformation and appearance variations, which can boost overall performance with negligible computation.
  arXiv  Detail & Related papers  (2023-08-09T15:32:03Z)
• 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)
• Transforming Model Prediction for Tracking [109.08417327309937]
  Transformers capture global relations with little inductive bias, allowing it to learn the prediction of more powerful target models. We train the proposed tracker end-to-end and validate its performance by conducting comprehensive experiments on multiple tracking datasets. Our tracker sets a new state of the art on three benchmarks, achieving an AUC of 68.5% on the challenging LaSOT dataset.
  arXiv  Detail & Related papers  (2022-03-21T17:59:40Z)
• Dynamic Template Selection Through Change Detection for Adaptive Siamese Tracking [7.662745552551165]
  Single object tracking (SOT) remains a challenging task in real-world application due to changes and deformations in a target object's appearance. We propose a new method for dynamic sample selection and memory replay, preventing template corruption. Our proposed method can be integrated into any object tracking algorithm that leverages online learning for model adaptation.
  arXiv  Detail & Related papers  (2022-03-07T07:27:02Z)
• Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking [82.34356879078955]
  We propose a compact memory embedding to enhance the discrimination of the segmentation-based deformable visual tracking method. Our method outperforms the excellent segmentation-based trackers, i.e., D3S and SiamMask on DAVIS 2017 benchmark.
  arXiv  Detail & Related papers  (2021-11-23T03:07:12Z)
• Target Transformed Regression for Accurate Tracking [30.516462193231888]
  This paper repurposes a Transformer-alike regression branch, termed as Target Transformed Regression (TREG) for accurate anchor-free tracking. The core to our TREG is to model pair-wise relation between elements in target template and search region, and use the resulted target enhanced visual representation for accurate bounding box regression. In addition, we devise a simple online template update mechanism to select reliable templates, increasing the robustness for appearance variations and geometric deformations of target in time.
  arXiv  Detail & Related papers  (2021-04-01T11:25:23Z)
• Graph Attention Tracking [76.19829750144564]
  We propose a simple target-aware Siamese graph attention network for general object tracking. Experiments on challenging benchmarks including GOT-10k, UAV123, OTB-100 and LaSOT demonstrate that the proposed SiamGAT outperforms many state-of-the-art trackers.
  arXiv  Detail & Related papers  (2020-11-23T04:26:45Z)
• ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking [80.02322563402758]
  One of the core components in online multiple object tracking (MOT) frameworks is associating new detections with existing tracklets. We introduce a probabilistic autoregressive generative model to score tracklet proposals by directly measuring the likelihood that a tracklet represents natural motion.
  arXiv  Detail & Related papers  (2020-04-16T06:43:11Z)

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.