Optimal Transport
النقل الأمثل
إطار رياضي يبحث عن الطريقة الأقل تكلفة لنقل الكتلة من توزيع إلى آخر. في SwAV، يُصاغ تعيين السمات إلى النماذج الأوّلية كمسألة نقل أمثل تُحلّ بخوارزمية سينكهورن-كنوب.
A mathematical framework that finds the least-cost way to transport mass from one distribution to another. In SwAV, feature-to-prototype assignment is formulated as an optimal transport problem solved by the Sinkhorn-Knopp algorithm.
Also translated asالنقل الأمثلي، مسألة النقل
First appears in this corpus in: SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (2020)
Appears in these papers
- Flow Matching for Generative Modeling2023in the sky ✦
- Flow Matching for Generative Modeling2023in the sky ✦
- SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments2020in the sky ✦
- SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments2020in the sky ✦