{"id":{"repo_id":"uic","oai_identifier":"oai:figshare.com:article/32995172"},"canonical_url":"https://search.dev.ndltd.org/etd/uic/oai:figshare.com:article/32995172","repository":{"repo_id":"uic","name":"University of Illinois - Chicago","base_url":"https://api.figshare.com/v2/oai"},"display":{"title":"Improved Out-of-Distribution Detection Using Segmented Images and Prompt-Only Text Reasoning","abstract":"The problem of Out-of-Distribution (OOD) detection has been thoroughly researched but continues to underperform in \"near-OOD\" settings, where OOD data may be very similar or inseparable from in-distribution (ID) data. The problem is that current state-of-the-art OOD detection methods fail to learn and utilize ID class-representative discriminative features effectively, while simultaneously demanding inaccessible amounts of resources. This thesis presents two OOD detection methods that exhibit state-of-the-art performance in near-OOD settings, one in the image data domain via the use of multi-view cross-attention processing of segmented images, and one in the text data domain using efficient and accessible prompt-only detection via alignment and scoring. The first approach leverages the segmented data and segmentation models to employ a multi-view method for image-based OOD detection, denoted as Cross-view Attention of Segmented views for OOD Detection (CASOD). Through the use of a pre-trained model and a novel cross-view correlation attention fusion architecture, discriminative features are learned across the original image and a foreground and background view, resulting in a highly informative ID class-relevant feature space. Utilizing distance-based OOD detection methods, CASOD achieves state-of-the-art performance over previous OOD detection baselines across a number of academically- or publicly-available datasets, including ImageNet, NINCO, SSB-Hard, iNaturalist, Textures, OpenImage-O, Places365, Species, and SUN. In particular, OOD detection performance on near-OOD datasets is shown to significantly improve. The second approach utilizes the inherent knowledge and reasoning capabilities in large language models (LLMs) to solve the task of prompt-only OOD detection, which requires only the use of text-prompting for OOD detection with no access to LLM components, logits, or outputs and no fine-tuning. Through prompting LLMs to perform lexical and semantic alignment before giving an OOD score for the input, OOD detection on academically- or publicly-available near-OOD datasets, including the Banking, CLINC, StackOverflow, 20NewsGroups, Dbpedia, and Snips datasets, can be significantly improved. Experiments demonstrate that this method, denoted as Alignment-based Thresholding for Prompt-only OOD detection (ATPO), not only outperforms the previous prompt-only OOD detection method but also outperforms strong traditional OOD detection methods with access to LLM features and logits.","abstract_html":"The problem of Out-of-Distribution (OOD) detection has been thoroughly researched but continues to underperform in "near-OOD" settings, where OOD data may be very similar or inseparable from in-distribution (ID) data. The problem is that current state-of-the-art OOD detection methods fail to learn and utilize ID class-representative discriminative features effectively, while simultaneously demanding inaccessible amounts of resources. This thesis presents two OOD detection methods that exhibit state-of-the-art performance in near-OOD settings, one in the image data domain via the use of multi-view cross-attention processing of segmented images, and one in the text data domain using efficient and accessible prompt-only detection via alignment and scoring. The first approach leverages the segmented data and segmentation models to employ a multi-view method for image-based OOD detection, denoted as Cross-view Attention of Segmented views for OOD Detection (CASOD). Through the use of a pre-trained model and a novel cross-view correlation attention fusion architecture, discriminative features are learned across the original image and a foreground and background view, resulting in a highly informative ID class-relevant feature space. Utilizing distance-based OOD detection methods, CASOD achieves state-of-the-art performance over previous OOD detection baselines across a number of academically- or publicly-available datasets, including ImageNet, NINCO, SSB-Hard, iNaturalist, Textures, OpenImage-O, Places365, Species, and SUN. In particular, OOD detection performance on near-OOD datasets is shown to significantly improve. The second approach utilizes the inherent knowledge and reasoning capabilities in large language models (LLMs) to solve the task of prompt-only OOD detection, which requires only the use of text-prompting for OOD detection with no access to LLM components, logits, or outputs and no fine-tuning. Through prompting LLMs to perform lexical and semantic alignment before giving an OOD score for the input, OOD detection on academically- or publicly-available near-OOD datasets, including the Banking, CLINC, StackOverflow, 20NewsGroups, Dbpedia, and Snips datasets, can be significantly improved. Experiments demonstrate that this method, denoted as Alignment-based Thresholding for Prompt-only OOD detection (ATPO), not only outperforms the previous prompt-only OOD detection method but also outperforms strong traditional OOD detection methods with access to LLM features and logits.","abstract_has_math":false,"creators":["Alexander Politowicz (24400118)"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-05-01T00:00:00Z","date_published":"2026-05-01T00:00:00Z","updated_at":"2026-07-27T21:33:50Z","subjects":["machine learning"],"languages":[],"rights":["In Copyright","Open Access after 2028-05-01"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.25417/uic.32995172.v1","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Alexander Politowicz (24400118)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026-05-01T00:00:00Z"]},{"key":"dc:relation","label":"Dc Relation","values":["https://figshare.com/articles/thesis/Improved_Out-of-Distribution_Detection_Using_Segmented_Images_and_Prompt-Only_Text_Reasoning/32995172"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["machine learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright","Open Access after 2028-05-01"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.25417/uic.32995172.v1"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The problem of Out-of-Distribution (OOD) detection has been thoroughly researched but continues to underperform in \"near-OOD\" settings, where OOD data may be very similar or inseparable from in-distribution (ID) data. The problem is that current state-of-the-art OOD detection methods fail to learn and utilize ID class-representative discriminative features effectively, while simultaneously demanding inaccessible amounts of resources. This thesis presents two OOD detection methods that exhibit state-of-the-art performance in near-OOD settings, one in the image data domain via the use of multi-view cross-attention processing of segmented images, and one in the text data domain using efficient and accessible prompt-only detection via alignment and scoring. The first approach leverages the segmented data and segmentation models to employ a multi-view method for image-based OOD detection, denoted as Cross-view Attention of Segmented views for OOD Detection (CASOD). Through the use of a pre-trained model and a novel cross-view correlation attention fusion architecture, discriminative features are learned across the original image and a foreground and background view, resulting in a highly informative ID class-relevant feature space. Utilizing distance-based OOD detection methods, CASOD achieves state-of-the-art performance over previous OOD detection baselines across a number of academically- or publicly-available datasets, including ImageNet, NINCO, SSB-Hard, iNaturalist, Textures, OpenImage-O, Places365, Species, and SUN. In particular, OOD detection performance on near-OOD datasets is shown to significantly improve. The second approach utilizes the inherent knowledge and reasoning capabilities in large language models (LLMs) to solve the task of prompt-only OOD detection, which requires only the use of text-prompting for OOD detection with no access to LLM components, logits, or outputs and no fine-tuning. Through prompting LLMs to perform lexical and semantic alignment before giving an OOD score for the input, OOD detection on academically- or publicly-available near-OOD datasets, including the Banking, CLINC, StackOverflow, 20NewsGroups, Dbpedia, and Snips datasets, can be significantly improved. Experiments demonstrate that this method, denoted as Alignment-based Thresholding for Prompt-only OOD detection (ATPO), not only outperforms the previous prompt-only OOD detection method but also outperforms strong traditional OOD detection methods with access to LLM features and logits."]},{"key":"dc:title","label":"Title","values":["Improved Out-of-Distribution Detection Using Segmented Images and Prompt-Only Text Reasoning"]}]}],"canonical_facts":{"dc:creator":["Alexander Politowicz (24400118)"],"dc:date":["2026-05-01T00:00:00Z"],"dc:description":["The problem of Out-of-Distribution (OOD) detection has been thoroughly researched but continues to underperform in \"near-OOD\" settings, where OOD data may be very similar or inseparable from in-distribution (ID) data. The problem is that current state-of-the-art OOD detection methods fail to learn and utilize ID class-representative discriminative features effectively, while simultaneously demanding inaccessible amounts of resources. This thesis presents two OOD detection methods that exhibit state-of-the-art performance in near-OOD settings, one in the image data domain via the use of multi-view cross-attention processing of segmented images, and one in the text data domain using efficient and accessible prompt-only detection via alignment and scoring. The first approach leverages the segmented data and segmentation models to employ a multi-view method for image-based OOD detection, denoted as Cross-view Attention of Segmented views for OOD Detection (CASOD). Through the use of a pre-trained model and a novel cross-view correlation attention fusion architecture, discriminative features are learned across the original image and a foreground and background view, resulting in a highly informative ID class-relevant feature space. Utilizing distance-based OOD detection methods, CASOD achieves state-of-the-art performance over previous OOD detection baselines across a number of academically- or publicly-available datasets, including ImageNet, NINCO, SSB-Hard, iNaturalist, Textures, OpenImage-O, Places365, Species, and SUN. In particular, OOD detection performance on near-OOD datasets is shown to significantly improve. The second approach utilizes the inherent knowledge and reasoning capabilities in large language models (LLMs) to solve the task of prompt-only OOD detection, which requires only the use of text-prompting for OOD detection with no access to LLM components, logits, or outputs and no fine-tuning. Through prompting LLMs to perform lexical and semantic alignment before giving an OOD score for the input, OOD detection on academically- or publicly-available near-OOD datasets, including the Banking, CLINC, StackOverflow, 20NewsGroups, Dbpedia, and Snips datasets, can be significantly improved. Experiments demonstrate that this method, denoted as Alignment-based Thresholding for Prompt-only OOD detection (ATPO), not only outperforms the previous prompt-only OOD detection method but also outperforms strong traditional OOD detection methods with access to LLM features and logits."],"dc:identifier":["10.25417/uic.32995172.v1"],"dc:relation":["https://figshare.com/articles/thesis/Improved_Out-of-Distribution_Detection_Using_Segmented_Images_and_Prompt-Only_Text_Reasoning/32995172"],"dc:rights":["In Copyright","Open Access after 2028-05-01"],"dc:subject":["machine learning"],"dc:title":["Improved Out-of-Distribution Detection Using Segmented Images and Prompt-Only Text Reasoning"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T21:33:50Z"}