Efficient Scale Estimation Methods using Lightweight Deep Convolutional Neural Networks for Visual Tracking

• URL: http://arxiv.org/abs/2004.02933v2
• Date: Fri, 11 Dec 2020 08:22:24 GMT
• Title: Efficient Scale Estimation Methods using Lightweight Deep Convolutional Neural Networks for Visual Tracking
• Authors: Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan, Shohreh Kasaei
• Abstract summary: This paper exploits pre-trained lightweight CNNs models to propose two efficient scale estimation methods. The proposed methods are formulated based on either holistic or region representation of convolutional feature maps. They exploit proposed one-pass feature extraction processes that significantly improve the computational efficiency.
• Score: 16.439797365064003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, visual tracking methods that are based on discriminative correlation filters (DCF) have been very promising. However, most of these methods suffer from a lack of robust scale estimation skills. Although a wide range of recent DCF-based methods exploit the features that are extracted from deep convolutional neural networks (CNNs) in their translation model, the scale of the visual target is still estimated by hand-crafted features. Whereas the exploitation of CNNs imposes a high computational burden, this paper exploits pre-trained lightweight CNNs models to propose two efficient scale estimation methods, which not only improve the visual tracking performance but also provide acceptable tracking speeds. The proposed methods are formulated based on either holistic or region representation of convolutional feature maps to efficiently integrate into DCF formulations to learn a robust scale model in the frequency domain. Moreover, against the conventional scale estimation methods with iterative feature extraction of different target regions, the proposed methods exploit proposed one-pass feature extraction processes that significantly improve the computational efficiency. Comprehensive experimental results on the OTB-50, OTB-100, TC-128 and VOT-2018 visual tracking datasets demonstrate that the proposed visual tracking methods outperform the state-of-the-art methods, effectively.

Related papers

• Consensus-Adaptive RANSAC [104.87576373187426]
  We propose a new RANSAC framework that learns to explore the parameter space by considering the residuals seen so far via a novel attention layer. The attention mechanism operates on a batch of point-to-model residuals, and updates a per-point estimation state to take into account the consensus found through a lightweight one-step transformer.
  arXiv  Detail & Related papers  (2023-07-26T08:25:46Z)
• Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation [151.70234052015948]
  We propose a novel approach that encourages the optimization algorithm to seek a flat trajectory. We show that the weights trained on synthetic data are robust against the accumulated errors perturbations with the regularization towards the flat trajectory. Our method, called Flat Trajectory Distillation (FTD), is shown to boost the performance of gradient-matching methods by up to 4.7%.
  arXiv  Detail & Related papers  (2022-11-20T15:49:11Z)
• Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
  There is an increasing need for active learning algorithms that are compatible with deep neural networks. This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
  arXiv  Detail & Related papers  (2021-06-17T17:26:31Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)
• Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation [22.688772441351308]
  Methods based on class activation mapping and randomized input sampling have gained great popularity. However, the attribution methods provide lower resolution and blurry explanation maps that limit their explanation power. In this work, we collect visualization maps from multiple layers of the model based on an attribution-based input sampling technique. We also propose a layer selection strategy that applies to the whole family of CNN-based models.
  arXiv  Detail & Related papers  (2020-10-01T20:27:30Z)
• Adaptive Exploitation of Pre-trained Deep Convolutional Neural Networks for Robust Visual Tracking [14.627458410954628]
  This paper provides a comprehensive analysis of four commonly used CNN models to determine the best feature maps of each model. With the aid of analysis results as attribute dictionaries, adaptive exploitation of deep features is proposed to improve the accuracy and robustness of visual trackers.
  arXiv  Detail & Related papers  (2020-08-29T17:09:43Z)
• Beyond Background-Aware Correlation Filters: Adaptive Context Modeling by Hand-Crafted and Deep RGB Features for Visual Tracking [16.439797365064003]
  An adaptive background-aware correlation filter-based tracker is proposed in this paper. It effectively models the target appearance by using either the histogram of oriented gradients (HOG) or convolutional neural network (CNN) feature maps. The proposed method exploits the fast 2D non-maximum suppression (NMS) algorithm and the semantic information comparison to detect challenging situations.
  arXiv  Detail & Related papers  (2020-04-06T18:48:39Z)
• Effective Fusion of Deep Multitasking Representations for Robust Visual Tracking [34.09763324745818]
  This paper aims to evaluate the performance of twelve state-of-the-art ResNet-based FENs in a DCF-based framework. It ranks their best feature maps and explores the generalized adoption of the best ResNet-based FEN into another DCF-based method. The proposed method extracts deep semantic information from a fully convolutional FEN and fuses it with the best ResNet-based feature maps to strengthen the target representation.
  arXiv  Detail & Related papers  (2020-04-03T05:33:59Z)
• Object-Adaptive LSTM Network for Real-time Visual Tracking with Adversarial Data Augmentation [31.842910084312265]
  We propose a novel real-time visual tracking method, which adopts an object-adaptive LSTM network to effectively capture the video sequential dependencies and adaptively learn the object appearance variations. Experiments on four visual tracking benchmarks demonstrate the state-of-the-art performance of our method in terms of both tracking accuracy and speed.
  arXiv  Detail & Related papers  (2020-02-07T03:06:07Z)
• Large Batch Training Does Not Need Warmup [111.07680619360528]
  Training deep neural networks using a large batch size has shown promising results and benefits many real-world applications. In this paper, we propose a novel Complete Layer-wise Adaptive Rate Scaling (CLARS) algorithm for large-batch training. Based on our analysis, we bridge the gap and illustrate the theoretical insights for three popular large-batch training techniques.
  arXiv  Detail & Related papers  (2020-02-04T23:03:12Z)
• NCVis: Noise Contrastive Approach for Scalable Visualization [79.44177623781043]
  NCVis is a high-performance dimensionality reduction method built on a sound statistical basis of noise contrastive estimation. We show that NCVis outperforms state-of-the-art techniques in terms of speed while preserving the representation quality of other methods.
  arXiv  Detail & Related papers  (2020-01-30T15:43:50Z)

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.