Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288261792> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4288261792 abstract "Energy minimization methods are a classical tool in a multitude of computer vision applications. While they are interpretable and well-studied, their regularity assumptions are difficult to design by hand. Deep learning techniques on the other hand are purely data-driven, often provide excellent results, but are very difficult to constrain to predefined physical or safety-critical models. A possible combination between the two approaches is to design a parametric energy and train the free parameters in such a way that minimizers of the energy correspond to desired solution on a set of training examples. Unfortunately, such formulations typically lead to bi-level optimization problems, on which common optimization algorithms are difficult to scale to modern requirements in data processing and efficiency. In this work, we present a new strategy to optimize these bi-level problems. We investigate surrogate single-level problems that majorize the target problems and can be implemented with existing tools, leading to efficient algorithms without collapse of the energy function. This framework of strategies enables new avenues to the training of parameterized energy minimization models from large data." @default.
- W4288261792 created "2022-07-28" @default.
- W4288261792 creator A5016208719 @default.
- W4288261792 creator A5049400969 @default.
- W4288261792 date "2019-08-16" @default.
- W4288261792 modified "2023-10-16" @default.
- W4288261792 title "Parametric Majorization for Data-Driven Energy Minimization Methods" @default.
- W4288261792 doi "https://doi.org/10.48550/arxiv.1908.06209" @default.
- W4288261792 hasPublicationYear "2019" @default.
- W4288261792 type Work @default.
- W4288261792 citedByCount "0" @default.
- W4288261792 crossrefType "posted-content" @default.
- W4288261792 hasAuthorship W4288261792A5016208719 @default.
- W4288261792 hasAuthorship W4288261792A5049400969 @default.
- W4288261792 hasBestOaLocation W42882617921 @default.
- W4288261792 hasConcept C105795698 @default.
- W4288261792 hasConcept C11413529 @default.
- W4288261792 hasConcept C117251300 @default.
- W4288261792 hasConcept C119857082 @default.
- W4288261792 hasConcept C126255220 @default.
- W4288261792 hasConcept C14036430 @default.
- W4288261792 hasConcept C147597530 @default.
- W4288261792 hasConcept C147764199 @default.
- W4288261792 hasConcept C14961307 @default.
- W4288261792 hasConcept C154945302 @default.
- W4288261792 hasConcept C165464430 @default.
- W4288261792 hasConcept C177264268 @default.
- W4288261792 hasConcept C185592680 @default.
- W4288261792 hasConcept C186370098 @default.
- W4288261792 hasConcept C199360897 @default.
- W4288261792 hasConcept C2780440489 @default.
- W4288261792 hasConcept C33923547 @default.
- W4288261792 hasConcept C41008148 @default.
- W4288261792 hasConcept C78458016 @default.
- W4288261792 hasConcept C86803240 @default.
- W4288261792 hasConceptScore W4288261792C105795698 @default.
- W4288261792 hasConceptScore W4288261792C11413529 @default.
- W4288261792 hasConceptScore W4288261792C117251300 @default.
- W4288261792 hasConceptScore W4288261792C119857082 @default.
- W4288261792 hasConceptScore W4288261792C126255220 @default.
- W4288261792 hasConceptScore W4288261792C14036430 @default.
- W4288261792 hasConceptScore W4288261792C147597530 @default.
- W4288261792 hasConceptScore W4288261792C147764199 @default.
- W4288261792 hasConceptScore W4288261792C14961307 @default.
- W4288261792 hasConceptScore W4288261792C154945302 @default.
- W4288261792 hasConceptScore W4288261792C165464430 @default.
- W4288261792 hasConceptScore W4288261792C177264268 @default.
- W4288261792 hasConceptScore W4288261792C185592680 @default.
- W4288261792 hasConceptScore W4288261792C186370098 @default.
- W4288261792 hasConceptScore W4288261792C199360897 @default.
- W4288261792 hasConceptScore W4288261792C2780440489 @default.
- W4288261792 hasConceptScore W4288261792C33923547 @default.
- W4288261792 hasConceptScore W4288261792C41008148 @default.
- W4288261792 hasConceptScore W4288261792C78458016 @default.
- W4288261792 hasConceptScore W4288261792C86803240 @default.
- W4288261792 hasLocation W42882617921 @default.
- W4288261792 hasOpenAccess W4288261792 @default.
- W4288261792 hasPrimaryLocation W42882617921 @default.
- W4288261792 hasRelatedWork W1483822002 @default.
- W4288261792 hasRelatedWork W2034595922 @default.
- W4288261792 hasRelatedWork W2096504025 @default.
- W4288261792 hasRelatedWork W2153731865 @default.
- W4288261792 hasRelatedWork W2351116219 @default.
- W4288261792 hasRelatedWork W2972785471 @default.
- W4288261792 hasRelatedWork W3091585071 @default.
- W4288261792 hasRelatedWork W4225307033 @default.
- W4288261792 hasRelatedWork W2471196694 @default.
- W4288261792 hasRelatedWork W2566606478 @default.
- W4288261792 isParatext "false" @default.
- W4288261792 isRetracted "false" @default.
- W4288261792 workType "article" @default.