A Self-Training Hierarchical Prototype-Based Approach for Semi-Supervised Classification

Xiaowei Gu

Allbwn ymchwil: Cyfraniad at gyfnodolynErthygladolygiad gan gymheiriaid

31 Dyfyniadau(SciVal)
53 Wedi eu Llwytho i Lawr (Pure)

Crynodeb

This paper introduces a novel self-training hierarchical prototype-based approach for semi-supervised classification. The proposed approach firstly identifies meaningful prototypes from labelled samples at multiple levels of granularity and, then, self-organizes a highly transparent, multi-layered recognition model by arranging them in a form of pyramidal hierarchies. After this, the learning model continues to self-evolve its structure and self-expand its knowledge base to incorporate new patterns recognized from unlabelled samples by exploiting the pseudo-label technique. Thanks to its prototype-based nature, the overall computational process of the proposed approach is highly explainable and traceable. Experimental studies with various benchmark image recognition problems demonstrate the state-of-the-art performance of the proposed approach, showing its strong capability to mine key information from unlabelled data for classification.
Iaith wreiddiolSaesneg
Tudalennau (o-i)204-224
Nifer y tudalennau21
CyfnodolynInformation Sciences
Cyfrol535
Dyddiad ar-lein cynnar13 Mai 2020
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsCyhoeddwyd - 01 Hyd 2020
Cyhoeddwyd yn allanolIe

Ôl bys

Gweld gwybodaeth am bynciau ymchwil 'A Self-Training Hierarchical Prototype-Based Approach for Semi-Supervised Classification'. Gyda’i gilydd, maen nhw’n ffurfio ôl bys unigryw.

Dyfynnu hyn