Brain-Inspired Computing, International Workshop, Cetraro/Italy, July 2013

How researchers see this paper

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

An End-to-End Architecture for Class-Incremental Object Detection with Knowledge Distillation (2019, methodology): “In addition to directly using the output of the classifier in CIFRCN, we can also adopt the nearest prototype (NP) classifier [16] to assign class labels to the proposals, since the NP classifier can be easily expanded by adding prototypes of the new classes, which is at low cost.”
Prototype-based models in machine learning. (2016, background): “only one of the two versions δγ(x, w) or δγ(w, x) consistently in training and working phase.(62,70) An application example for the use of nonsymmetric divergences in LVQ classifiers is presented in Ref 70.”
Prototype-based Neural Network Layers: Incorporating Vector Quantization (2018, background): “Non-standard metrics are also attractive for PBs [28, 37, 38, 39] since their incorporation provides a powerful modification.”
Rethinking Semantic Segmentation: A Prototype View (2022, background): “3 intuitively shows that prototype based learners make metric comparisons of data [8].”