{"id":69119,"date":"2024-09-23T15:41:40","date_gmt":"2024-09-23T07:41:40","guid":{"rendered":"https:\/\/inventec2.mjitec.tw\/?page_id=69119"},"modified":"2024-09-23T18:11:45","modified_gmt":"2024-09-23T10:11:45","slug":"learning-multi-manifold-embedding-for-out-of-distribution-detection","status":"publish","type":"page","link":"https:\/\/inventec2.mjitec.tw\/en\/ai\/learning-multi-manifold-embedding-for-out-of-distribution-detection\/","title":{"rendered":"Learning Multi-Manifold Embedding for Out-Of-Distribution Detection"},"content":{"rendered":"

[vc_row full_width=”stretch_row”][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[vc_row_inner el_class=”md-full-col”][vc_column_inner el_class=”m_p” width=”1\/2″]\n
\n \t
\n \t\t\n\t \n\t

Learning Multi-Manifold Embedding for Out-Of-Distribution Detection <\/h2>\n\t <\/div><\/div>[vc_column_text css=”.vc_custom_1727076166097{margin-bottom: 20px !important;}”]2024 European Conference on Computer Vision Workshop (ECCVW2024)[\/vc_column_text][vc_column_text css=”.vc_custom_1727078953848{margin-bottom: 5px !important;}”]<\/p>\n
\n
Authors<\/h6>\n<\/div>\n

[\/vc_column_text][vc_column_text css=”.vc_custom_1727076182809{margin-bottom: 20px !important;}”]Jeng-Lin Li, Ming-Ching Chang, and Wei-Chao Chen[\/vc_column_text][vc_column_text css=”.vc_custom_1727078971469{margin-bottom: 5px !important;}”]<\/p>\n

\n
Published<\/h6>\n<\/div>\n

[\/vc_column_text][vc_column_text css=””]2024\/9\/29[\/vc_column_text][\/vc_column_inner][vc_column_inner el_class=”m_p” width=”1\/2″][vc_single_image image=”69121″ img_size=”full” css=””][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row full_width=”stretch_row”][vc_column][vc_row_inner content_placement=”top” css=”.vc_custom_1657794580528{margin-bottom: 20px !important;}”][vc_column_inner el_class=”m_p paragraph_title” width=”1\/3″]\n
\n \t
\n \t\t\n\t \n\t

Abstract <\/h2>\n\t <\/div><\/div>[\/vc_column_inner][vc_column_inner el_class=”m_p” width=”2\/3″][vc_column_text css=””]Detecting out-of-distribution (OOD) samples is crucial for trustworthy AI in real-world applications. Leveraging recent advances in representation learning and latent embeddings, Various scoring algorithms estimate distributions beyond the training data. However, a single embedding space falls short in characterizing in-distribution data and defending against diverse OOD conditions.<\/p>\n

This paper introduces a novel Multi-Manifold Embedding Learning (MMEL) framework, optimizing hypersphere and hyperbolic spaces jointly for enhanced OOD detection. MMEL generates representative embeddings and employs a prototype-aware scoring function to differentiate OOD samples.<\/p>\n

Experiments on six open datasets demonstrate MMEL’s significant reduction in FPR while maintaining a high AUC compared to state-of-the-art distance-based OOD detection methods.<\/p>\n

Notably, enrolling ten OOD samples without retraining achieves comparable FPR and AUC to modern outlier exposure methods using 80 million outlier samples for model training.[\/vc_column_text][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row][vc_column width=”1\/3″ el_class=”m_p keyword_title”][vc_column_text css=””]<\/p>\n

Keywords<\/h2>\n

[\/vc_column_text][\/vc_column][vc_column width=”2\/3″ el_class=”m_p keyword”][vc_row_inner content_placement=”middle”][vc_column_inner width=”1\/3″][vc_raw_html css=””]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VPdXQtb2YtZGlzdHJpYnV0aW9uJTIwZGV0ZWN0aW9uJTNDJTJGbGklM0UlMEElMjAlMDklM0NsaSUyMHN0eWxlJTNEJTIybGluZS1oZWlnaHQlM0EzNHB4JTNCJTIyJTNFSHlwZXJib2xpYyUzQyUyRmxpJTNFJTBBJTNDJTJGdWwlM0U=[\/vc_raw_html][\/vc_column_inner][vc_column_inner width=”1\/3″][vc_raw_html css=””]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VNdWx0aXBsZSUyMG1hbmlmb2xkJTIwbGVhcm5pbmclM0MlMkZsaSUzRSUwQSUzQyUyRnVsJTNF[\/vc_raw_html][\/vc_column_inner][vc_column_inner width=”1\/3″][vc_raw_html css=””]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VIeXBlcnNwaGVyZSUzQyUyRmxpJTNFJTBBJTNDJTJGdWwlM0U=[\/vc_raw_html][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row full_width=”stretch_row” el_class=”bg” css=”.vc_custom_1657248474326{padding-top: 50px !important;padding-bottom: 50px !important;}”][vc_column][vc_column_text css=”.vc_custom_1727079093363{margin-bottom: 20px !important;}”]<\/p>\n

Download<\/span><\/h3>\n

[\/vc_column_text][vc_row_inner content_placement=”middle”][vc_column_inner el_class=”download_btn_wrap”][vc_btn title=”PDF” style=”flat” color=”white” align=”center” css=”” link=”url:https%3A%2F%2Farxiv.org%2Fabs%2F2409.12479|target:_blank” el_class=”download_btn”][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row]<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"

[vc_row full_width=”stretch_row”][vc_column][vc_row_inner el_class=”md-full-col”][vc_column_inner el_class=”m_p” width=”1\/2″][vc_column_text css=”.vc_custom_1727076166097{margin-bottom: 20px !important;}”]2024 European Conference on Computer Vision Workshop (ECCVW2024)[\/vc_column_text][vc_column_text css=”.vc_custom_1727078953848{margin-bottom: 5px !important;}”] Authors [\/vc_column_text][vc_column_text css=”.vc_custom_1727076182809{margin-bottom: 20px !important;}”]Jeng-Lin Li, Ming-Ching Chang, and Wei-Chao Chen[\/vc_column_text][vc_column_text css=”.vc_custom_1727078971469{margin-bottom: 5px !important;}”] Published [\/vc_column_text][vc_column_text css=””]2024\/9\/29[\/vc_column_text][\/vc_column_inner][vc_column_inner el_class=”m_p” width=”1\/2″][vc_single_image image=”69121″ img_size=”full” css=””][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column][\/vc_column][\/vc_row][vc_row full_width=”stretch_row”][vc_column][vc_row_inner content_placement=”top” css=”.vc_custom_1657794580528{margin-bottom: 20px !important;}”][vc_column_inner el_class=”m_p paragraph_title” width=”1\/3″][\/vc_column_inner][vc_column_inner el_class=”m_p” width=”2\/3″][vc_column_text css=””]Detecting out-of-distribution (OOD) samples is…<\/p>\n","protected":false},"author":4,"featured_media":0,"parent":4975,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-69119","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages\/69119","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/comments?post=69119"}],"version-history":[{"count":3,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages\/69119\/revisions"}],"predecessor-version":[{"id":69989,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages\/69119\/revisions\/69989"}],"up":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages\/4975"}],"wp:attachment":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/media?parent=69119"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}