{"id":9554,"date":"2026-01-07T07:03:13","date_gmt":"2026-01-07T07:03:13","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2026\/01\/07\/2601-02440\/"},"modified":"2026-01-07T07:03:13","modified_gmt":"2026-01-07T07:03:13","slug":"2601-02440","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2026\/01\/07\/2601-02440\/","title":{"rendered":"Mitigating Long-Tailed Anomaly Score Distributions with Importance-Weighted Loss"},"content":{"rendered":"

Mitigating Long-Tailed Anomaly Score Distributions with Importance-Weighted Loss
\n \t

\n
<\/BR>
\n
\n \t

\n
<\/BR><\/p>\n

arXiv:2601.02440v1 Announce Type: new
\nAbstract: Anomaly detection is crucial in industrial applications for identifying rare and unseen patterns to ensure system reliability. Traditional models, trained on a single class of normal data, struggle with real-world distributions where normal data exhibit diverse patterns, leading to class imbalance and long-tailed anomaly score distributions (LTD). This imbalance skews model training and degrades detection performance, especially for minority instances. To address this issue, we propose a novel importance-weighted loss designed specifically for anomaly detection. Compared to the previous method for LTD in classification, our method does not require prior knowledge of normal data classes. Instead, we introduce a weighted loss function that incorporates importance sampling to align the distribution of anomaly scores with a target Gaussian, ensuring a balanced representation of normal data. Extensive experiments on three benchmark image datasets and three real-world hyperspectral imaging datasets demonstrate the robustness of our approach in mitigating LTD-induced bias. Our method improves anomaly detection performance by 0.043, highlighting its effectiveness in real-world applications.<\/div>\n

\t

\n
<\/BR>
\n Jungi Lee, Jungkwon Kim, Chi Zhang, Sangmin Kim, Kwangsun Yoo, Seok-Joo Byun
\n \t

\n
<\/BR>
\nGo to original source<\/a>
\n \t

\n
<\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"

Mitigating Long-Tailed Anomaly Score Distributions with Importance-Weighted Loss arXiv:2601.02440v1 Announce Type: new Abstract: Anomaly detection is crucial in industrial applications for identifying rare and unseen patterns to ensure system reliability. Traditional models, trained on a single class of normal data, struggle with real-world distributions where normal data exhibit diverse patterns, leading to class imbalance and […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,187,113,112],"tags":[1501,335,1524],"class_list":["post-9554","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-ai","category-cs-lg","category-stat-ml","tag-anomaly","tag-distributions","tag-importance"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/9554"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=9554"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/9554\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=9554"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=9554"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=9554"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}