國立虎尾科技大學 |

Downstream Task Self-Supervised Learning for Object Recognition and Tracking.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Downstream Task Self-Supervised Learning for Object Recognition and Tracking./
Author:	Siddique, Abubakar.
Description:	1 online resource (201 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 84-10, Section: B.
Contained By:	Dissertations Abstracts International84-10B.
Subject:	Computer engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9798379423124

Downstream Task Self-Supervised Learning for Object Recognition and Tracking.
Siddique, Abubakar.

Downstream Task Self-Supervised Learning for Object Recognition and Tracking. - 1 online resource (201 pages)

Source: Dissertations Abstracts International, Volume: 84-10, Section: B.

Thesis (Ph.D.)--Marquette University, 2023.

Includes bibliographical references

This dissertation addresses three limitations of deep learning methods in image and video understanding-based machine vision applications. Firstly, although deep convolutional neural networks (CNNs) are efficient for image recognition applications such as object detection and segmentation, they perform poorly under perspective distortions. In real-world applications, the camera perspective is a common problem that we can address by annotating large amounts of data, thus limiting the applicability of the deep learning models. Secondly, the typical approach for single-camera tracking problems is to use separate motion and appearance models, which are expensive in terms of computations and training data requirements. Finally, conventional multi-camera video understanding techniques use supervised learning algorithms to determine temporal relationships among objects. In large-scale applications, these methods are also limited by the requirement of extensive manually annotated data and computational resources.To address these limitations, we develop an uncertainty-aware self-supervised learning (SSL) technique that captures a model's instance or semantic segmentation uncertainty from overhead images and guides the model to learn the impact of the new perspective on object appearance. The test-time data augmentation-based pseudo-label refinement technique continuously trains a model until convergence on new perspective images. The proposed method can be applied for both self-supervision and semi-supervision, thus increasing the effectiveness of a deep pre-trained model in new domains. Extensive experiments demonstrate the effectiveness of the SSL technique in both object detection and semantic segmentation problems.In video understanding applications, we introduce simultaneous segmentation and tracking as an unsupervised spatio-temporal latent feature clustering problem. The jointly learned multi-task features leverage the task-dependent uncertainty to generate discriminative features in multi-object videos. Experiments have shown that the proposed tracker outperforms several state-of-the-art supervised methods. Finally, we proposed an unsupervised multi-camera tracklet association (MCTA) algorithm to track multiple objects in real-time. MCTA leverages the self-supervised detector model for single-camera tracking and solves the multi-camera tracking problem using multiple pair-wise camera associations modeled as a connected graph. The graph optimization method generates a global solution for partially or fully overlapping camera networks.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798379423124Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Data augmentationIndex Terms--Genre/Form:

554714
Electronic books.

Downstream Task Self-Supervised Learning for Object Recognition and Tracking.
LDR:04018ntm a22004097 4500 001 1150249
005 20241028114727.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379423124
035 $a (MiAaPQ)AAI30421089
035 $a AAI30421089
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Siddique, Abubakar. $3 1476696
245 1 0 $a Downstream Task Self-Supervised Learning for Object Recognition and Tracking.
264 0 $c 2023
300 $a 1 online resource (201 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-10, Section: B.
500 $a Advisor: Hayat, Majeed;Medeiros, Henry.
502 $a Thesis (Ph.D.)--Marquette University, 2023.
504 $a Includes bibliographical references
520 $a This dissertation addresses three limitations of deep learning methods in image and video understanding-based machine vision applications. Firstly, although deep convolutional neural networks (CNNs) are efficient for image recognition applications such as object detection and segmentation, they perform poorly under perspective distortions. In real-world applications, the camera perspective is a common problem that we can address by annotating large amounts of data, thus limiting the applicability of the deep learning models. Secondly, the typical approach for single-camera tracking problems is to use separate motion and appearance models, which are expensive in terms of computations and training data requirements. Finally, conventional multi-camera video understanding techniques use supervised learning algorithms to determine temporal relationships among objects. In large-scale applications, these methods are also limited by the requirement of extensive manually annotated data and computational resources.To address these limitations, we develop an uncertainty-aware self-supervised learning (SSL) technique that captures a model's instance or semantic segmentation uncertainty from overhead images and guides the model to learn the impact of the new perspective on object appearance. The test-time data augmentation-based pseudo-label refinement technique continuously trains a model until convergence on new perspective images. The proposed method can be applied for both self-supervision and semi-supervision, thus increasing the effectiveness of a deep pre-trained model in new domains. Extensive experiments demonstrate the effectiveness of the SSL technique in both object detection and semantic segmentation problems.In video understanding applications, we introduce simultaneous segmentation and tracking as an unsupervised spatio-temporal latent feature clustering problem. The jointly learned multi-task features leverage the task-dependent uncertainty to generate discriminative features in multi-object videos. Experiments have shown that the proposed tracker outperforms several state-of-the-art supervised methods. Finally, we proposed an unsupervised multi-camera tracklet association (MCTA) algorithm to track multiple objects in real-time. MCTA leverages the self-supervised detector model for single-camera tracking and solves the multi-camera tracking problem using multiple pair-wise camera associations modeled as a connected graph. The graph optimization method generates a global solution for partially or fully overlapping camera networks.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 569006
650 4 $a Electrical engineering. $3 596380
653 $a Data augmentation
653 $a Downstream tasks
653 $a Multi-view tracking
653 $a Object recognition
653 $a Self-supervised learning
653 $a Semantic segmentation
655 7 $a Electronic books. $2 local $3 554714
690 $a 0464
690 $a 0544
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Marquette University. $b Electrical & Computer Engineering. $3 1475970
773 0 $t Dissertations Abstracts International $g 84-10B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30421089 $z click for full text (PQDT)