Empirical Minimum Bayes Risk Prediction: How to Extract an Extra Few % Performance from Vision Models with Just Three More Parameters

26 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

DISCO Nets : DISsimilarity COefficients Networks (2016, methodology): “y2R d y and z2R z. Pointwise Prediction. In order to obtain a single prediction yfor a given input x, DISCO Nets use the principle of Maximum Expected Utility (MEU), similarly to Premachandran et al. [19]. 3 The prediction y task maximises the expected utility, or rather minimises the expected task-”
Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation (2016, methodology): “Based on the fact that the EIoEU is exact for a delta distribution, they take the idea of approximating EIoU from [11] by taking the average of EIoEU as computed in [10].”
Resolving Language and Vision Ambiguities Together: Joint Segmentation & Prepositional Attachment Resolution in Captioned Scenes (2016, background): “In Section 4, we describe each of the modules in detail, making concrete their respective features, and other details.”