Adaptive Exploitation of Pre-trained Deep Convolutional Neural Networks for Robust Visual Tracking

• URL: http://arxiv.org/abs/2008.13015v2
• Date: Tue, 22 Dec 2020 06:57:23 GMT
• Title: Adaptive Exploitation of Pre-trained Deep Convolutional Neural Networks for Robust Visual Tracking
• Authors: Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan, and Shohreh Kasaei
• Abstract summary: 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.
• Score: 14.627458410954628
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to the automatic feature extraction procedure via multi-layer nonlinear transformations, the deep learning-based visual trackers have recently achieved great success in challenging scenarios for visual tracking purposes. Although many of those trackers utilize the feature maps from pre-trained convolutional neural networks (CNNs), the effects of selecting different models and exploiting various combinations of their feature maps are still not compared completely. To the best of our knowledge, all those methods use a fixed number of convolutional feature maps without considering the scene attributes (e.g., occlusion, deformation, and fast motion) that might occur during tracking. As a pre-requisition, this paper proposes adaptive discriminative correlation filters (DCF) based on the methods that can exploit CNN models with different topologies. First, the paper provides a comprehensive analysis of four commonly used CNN models to determine the best feature maps of each model. Second, 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 regarding video characteristics. Third, the generalization of the proposed method is validated on various tracking datasets as well as CNN models with similar architectures. Finally, extensive experimental results demonstrate the effectiveness of the proposed adaptive method compared with state-of-the-art visual tracking methods.

Related papers

• Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective [64.04617968947697]
  We introduce a novel data-model co-design perspective: to promote superior weight sparsity. Specifically, customized Visual Prompts are mounted to upgrade neural Network sparsification in our proposed VPNs framework.
  arXiv  Detail & Related papers  (2023-12-03T13:50:24Z)
• DeepDC: Deep Distance Correlation as a Perceptual Image Quality Evaluator [53.57431705309919]
  ImageNet pre-trained deep neural networks (DNNs) show notable transferability for building effective image quality assessment (IQA) models. We develop a novel full-reference IQA (FR-IQA) model based exclusively on pre-trained DNN features. We conduct comprehensive experiments to demonstrate the superiority of the proposed quality model on five standard IQA datasets.
  arXiv  Detail & Related papers  (2022-11-09T14:57:27Z)
• FuNNscope: Visual microscope for interactively exploring the loss landscape of fully connected neural networks [77.34726150561087]
  We show how to explore high-dimensional landscape characteristics of neural networks. We generalize observations on small neural networks to more complex systems. An interactive dashboard opens up a number of possible application networks.
  arXiv  Detail & Related papers  (2022-04-09T16:41:53Z)
• 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)
• Auto-weighted Multi-view Feature Selection with Graph Optimization [90.26124046530319]
  We propose a novel unsupervised multi-view feature selection model based on graph learning. The contributions are threefold: (1) during the feature selection procedure, the consensus similarity graph shared by different views is learned. Experiments on various datasets demonstrate the superiority of the proposed method compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-04-11T03:25:25Z)
• Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection [55.888835686183995]
  We propose a neural network-based meta-learning method for supervised anomaly detection. We experimentally demonstrate that the proposed method achieves better performance than existing anomaly detection and few-shot learning methods.
  arXiv  Detail & Related papers  (2021-03-01T01:43:04Z)
• Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking [1.7188280334580193]
  We propose an adaptive combination of several CNN layers in a single DCF tracker to address variations of the target appearances. Experiments demonstrate that using the additional implicit data layers of CNNs significantly improves the tracker.
  arXiv  Detail & Related papers  (2020-10-02T21:16:26Z)
• A Detailed Look At CNN-based Approaches In Facial Landmark Detection [5.774786149181392]
  CNN-based approaches can be divided into regression and heatmap approaches. In this paper, we investigate both CNN-based approaches, generalize their advantages and disadvantages, and introduce a variation of the heatmap approach. A comprehensive evaluation is conducted and the result shows that the proposed model outperforms other models in all tested datasets.
  arXiv  Detail & Related papers  (2020-05-08T16:17:42Z)
• Efficient Scale Estimation Methods using Lightweight Deep Convolutional Neural Networks for Visual Tracking [16.439797365064003]
  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.
  arXiv  Detail & Related papers  (2020-04-06T18:49:37Z)
• 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)

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.