{"id":444,"date":"2024-12-09T07:01:01","date_gmt":"2024-12-09T07:01:01","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2024\/12\/09\/2412-04648\/"},"modified":"2024-12-09T07:01:01","modified_gmt":"2024-12-09T07:01:01","slug":"2412-04648","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2024\/12\/09\/2412-04648\/","title":{"rendered":"Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise"},"content":{"rendered":"

Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise
\n \t

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

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

arXiv:2412.04648v1 Announce Type: cross
\nAbstract: Recorrupted-to-Recorrupted (R2R) has emerged as a methodology for training deep networks for image restoration in a self-supervised manner from noisy measurement data alone, demonstrating equivalence in expectation to the supervised squared loss in the case of Gaussian noise. However, its effectiveness with non-Gaussian noise remains unexplored. In this paper, we propose Generalized R2R (GR2R), extending the R2R framework to handle a broader class of noise distribution as additive noise like log-Rayleigh and address the natural exponential family including Poisson and Gamma noise distributions, which play a key role in many applications including low-photon imaging and synthetic aperture radar. We show that the GR2R loss is an unbiased estimator of the supervised loss and that the popular Stein’s unbiased risk estimator can be seen as a special case. A series of experiments with Gaussian, Poisson, and Gamma noise validate GR2R’s performance, showing its effectiveness compared to other self-supervised methods.<\/div>\n

\t

\n
<\/BR>
\n Brayan Monroy, Jorge Bacca, Juli’an Tachella
\n \t

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

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

Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise arXiv:2412.04648v1 Announce Type: cross Abstract: Recorrupted-to-Recorrupted (R2R) has emerged as a methodology for training deep networks for image restoration in a self-supervised manner from noisy measurement data alone, demonstrating equivalence in expectation to the supervised squared loss in the case of Gaussian noise. However, its effectiveness with non-Gaussian […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,551,112],"tags":[455,552,553],"class_list":["post-444","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-eess-iv","category-stat-ml","tag-noise","tag-recorrupted","tag-supervised"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/444"}],"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=444"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/444\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=444"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=444"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=444"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}