{"id":{"repo_id":"sdstate","oai_identifier":"oai:openprairie.sdstate.edu:etd2-3033"},"canonical_url":"https://search.ndltd.org/etd/sdstate/oai:openprairie.sdstate.edu:etd2-3033","repository":{"repo_id":"sdstate","name":"South Dakota State University","base_url":"https://openprairie.sdstate.edu/do/oai/"},"display":{"title":"Fast and Sustainable Video Anomaly Detection with Continual Learning","abstract":"Real-time video anomaly detection systems deployed in surveillance, healthcare, and industrial environments face continuous distribution shifts in lighting, viewpoint, and activity patterns. Existing models often experience performance degradation under these conditions and may suffer catastrophic forgetting when adapting to new environments. This thesis proposes RegiGrow, a parameter-efficient continual adaptation framework built on the Flashback retrieval pipeline. RegiGrow integrates Mixture-of-Experts Low-Rank Adaptation into a frozen ImageBind encoder, enabling sequential domain adaptation without modifying the pretrained backbone. A lightweight router maps visual regime features to a distribution over LoRA experts, each specializing in a distinct normal operating regime. The central contribution is an entropy-triggered expert growth mechanism that dynamically expands model capacity in response to detected distribution shift. Catastrophic forgetting is mitigated through a class-balanced experience replay buffer preserving representative segments from prior domains. RegiGrow is evaluated under a continual learning protocol across UCF-Crime, ShanghaiTech, and UBnormal, with sequential training and cross-phase evaluation. The system achieves a final average AUROC of 0.6678, demonstrating positive backward transfer (+0.0136) and strong forward transfer to unseen domains (+0.1119 on ShanghaiTech, +0.0727 on UBnormal) without catastrophic forgetting.","abstract_html":"Real-time video anomaly detection systems deployed in surveillance, healthcare, and industrial environments face continuous distribution shifts in lighting, viewpoint, and activity patterns. Existing models often experience performance degradation under these conditions and may suffer catastrophic forgetting when adapting to new environments. This thesis proposes RegiGrow, a parameter-efficient continual adaptation framework built on the Flashback retrieval pipeline. RegiGrow integrates Mixture-of-Experts Low-Rank Adaptation into a frozen ImageBind encoder, enabling sequential domain adaptation without modifying the pretrained backbone. A lightweight router maps visual regime features to a distribution over LoRA experts, each specializing in a distinct normal operating regime. The central contribution is an entropy-triggered expert growth mechanism that dynamically expands model capacity in response to detected distribution shift. Catastrophic forgetting is mitigated through a class-balanced experience replay buffer preserving representative segments from prior domains. RegiGrow is evaluated under a continual learning protocol across UCF-Crime, ShanghaiTech, and UBnormal, with sequential training and cross-phase evaluation. The system achieves a final average AUROC of 0.6678, demonstrating positive backward transfer (+0.0136) and strong forward transfer to unseen domains (+0.1119 on ShanghaiTech, +0.0727 on UBnormal) without catastrophic forgetting.","abstract_has_math":false,"creators":["Amasa, Preethi"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis - Open Access","degree_discipline":"Electrical Engineering and Computer Science","degree_department":null,"school":null,"contributors":["Chulwoo Pack"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T09:06:09Z","subjects":["Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://openprairie.sdstate.edu/etd2/2021","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://openprairie.sdstate.edu/etd2/2021","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://openprairie.sdstate.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopenprairie.sdstate.edu%3Aetd2-3033","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chulwoo Pack"]},{"key":"dc:creator","label":"Author","values":["Amasa, Preethi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-05-11T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering and Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis - Open Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical and Computer Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://openprairie.sdstate.edu/etd2/2021"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Real-time video anomaly detection systems deployed in surveillance, healthcare, and industrial environments face continuous distribution shifts in lighting, viewpoint, and activity patterns. Existing models often experience performance degradation under these conditions and may suffer catastrophic forgetting when adapting to new environments. This thesis proposes RegiGrow, a parameter-efficient continual adaptation framework built on the Flashback retrieval pipeline. RegiGrow integrates Mixture-of-Experts Low-Rank Adaptation into a frozen ImageBind encoder, enabling sequential domain adaptation without modifying the pretrained backbone. A lightweight router maps visual regime features to a distribution over LoRA experts, each specializing in a distinct normal operating regime. The central contribution is an entropy-triggered expert growth mechanism that dynamically expands model capacity in response to detected distribution shift. Catastrophic forgetting is mitigated through a class-balanced experience replay buffer preserving representative segments from prior domains. RegiGrow is evaluated under a continual learning protocol across UCF-Crime, ShanghaiTech, and UBnormal, with sequential training and cross-phase evaluation. The system achieves a final average AUROC of 0.6678, demonstrating positive backward transfer (+0.0136) and strong forward transfer to unseen domains (+0.1119 on ShanghaiTech, +0.0727 on UBnormal) without catastrophic forgetting."]},{"key":"dc:title","label":"Title","values":["Fast and Sustainable Video Anomaly Detection with Continual Learning"]}]}],"canonical_facts":{"dc:contributor":["Chulwoo Pack"],"dc:creator":["Amasa, Preethi"],"dc:date.available":["2026-05-11T07:00:00Z"],"dc:date.created":["2026-01-01T08:00:00Z"],"dc:description.abstract":["Real-time video anomaly detection systems deployed in surveillance, healthcare, and industrial environments face continuous distribution shifts in lighting, viewpoint, and activity patterns. Existing models often experience performance degradation under these conditions and may suffer catastrophic forgetting when adapting to new environments. This thesis proposes RegiGrow, a parameter-efficient continual adaptation framework built on the Flashback retrieval pipeline. RegiGrow integrates Mixture-of-Experts Low-Rank Adaptation into a frozen ImageBind encoder, enabling sequential domain adaptation without modifying the pretrained backbone. A lightweight router maps visual regime features to a distribution over LoRA experts, each specializing in a distinct normal operating regime. The central contribution is an entropy-triggered expert growth mechanism that dynamically expands model capacity in response to detected distribution shift. Catastrophic forgetting is mitigated through a class-balanced experience replay buffer preserving representative segments from prior domains. RegiGrow is evaluated under a continual learning protocol across UCF-Crime, ShanghaiTech, and UBnormal, with sequential training and cross-phase evaluation. The system achieves a final average AUROC of 0.6678, demonstrating positive backward transfer (+0.0136) and strong forward transfer to unseen domains (+0.1119 on ShanghaiTech, +0.0727 on UBnormal) without catastrophic forgetting."],"dc:identifier":["https://openprairie.sdstate.edu/etd2/2021"],"dc:rights":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Electrical and Computer Engineering"],"dc:title":["Fast and Sustainable Video Anomaly Detection with Continual Learning"],"thesis:degree_discipline":["Electrical Engineering and Computer Science"],"thesis:degree_level":["Thesis - Open Access"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T09:06:09Z"}