Off-campus UNL users: To download campus access dissertations, please use the following link to log into our proxy server with your NU ID and password. When you are done browsing please remember to return to this page and log out.
Non-UNL users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Weakly Supervised Attention-Based Recognition Under Spectral, Turbulence, and Resource Variations
Abstract
While supervised optimization paradigms are ubiquitous across diverse recognition systems, the risk of over-fitting and increasing bias have limited their applicability.This dissertation focuses on unsupervised learning—learning without precisely curated data—and argues that unsupervised learning methods can enable both discriminability and generalizability. Through the use of attention-based machine learning and advanced clustering, unsupervised methods are able to focus on fine-grained information in images without any explicit supervision. The dissertation introduces a domain-bridging framework for tasks like cross-spectrum matching and long-range recognition, utilizing intra-domain clustering and inter-domain matching to generate pseudo-labels. Additionally, a hash-based network is proposed to accelerate the search process, with dynamic capabilities for computational adjustment based on operational demands or input complexity.The overall framework is demonstrated over biometric tasks, such as person re-identification and facial recognition, and shows superiority in performance and efficiency compared to other unsupervised methods, and in some cases even supervised methods.
Subject Area
Artificial intelligence|Computer science|Information science|Applied Mathematics
Recommended Citation
Nikhal, Kshitij Naresh, "Weakly Supervised Attention-Based Recognition Under Spectral, Turbulence, and Resource Variations" (2024). ETD collection for University of Nebraska-Lincoln. AAI30997460.
https://digitalcommons.unl.edu/dissertations/AAI30997460