DeepNCM: Deep Nearest Class Mean Classifiers

51 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.

Online Continual Learning Via Candidates Voting (2021, methodology): “Therefore, we propose to use an online dynamic class mean update criteria [12] for exemplar selection, which does not require knowing the total number of data beforehand as shown in Equation 1.”
ProtoGAN: Towards Few Shot Learning for Action Recognition (2019, methodology): “When the number of samples belonging to the class is high, statistical methods like mean of the samples tend to accurately represent those semantics [7].”
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation (2020, methodology): “Baseline: original model result; 2fc ncm [15]: we have tried to adopt the deep nearest class mean classifier learned with 2fc representation.”
Rethinking Semantic Segmentation: A Prototype View (2022, background): “There has been a recent surge of interest to integrate deep learning into prototype learning, showing good potential in few-shot [98], zero-shot [54], and unsupervised learning [116, 120], as well as supervised classification [38, 83, 115, 123] and interpretable networks [65].”